技术领域technical field
本发明涉及图像处理技术领域，特别是涉及一种合影照片生成方法及其装置、移动终端。The present invention relates to the technical field of image processing, in particular to a method for generating a group photo, a device thereof, and a mobile terminal.
背景技术Background technique
随着年龄增长，每个人的生活开始变得越来越独立，朋友和家人聚在一起的时光越来越难得，旅游的时间也越来越少。在想要合照的时候有朋友不在，或者想旅游的时候没有时间，总会留有遗憾，一般我们可以通过后期的修图来实现合照的愿望。As we grow older, everyone's life begins to become more and more independent, with friends and family spending less and less time together, and less and less time to travel. When you want to take a group photo, if your friends are not there, or if you don’t have time when you want to travel, there will always be regrets. Generally, we can realize the desire to take a group photo through post-editing.
发明人在实现本发明的过程中，发现相关技术至少存在以下问题：一方面通过后期修图无法实现在拍照的当时时刻,与联系人的进行实时互动；另一方面,利用后期的Photoshop等图像处理软件生成的异地合照，会有一些限制，例如，存在人物光影不对、动作不合适等问题。In the process of realizing the present invention, the inventor found that there are at least the following problems in related technologies: on the one hand, it is impossible to realize real-time interaction with contacts at the moment of taking pictures through post-editing; on the other hand, using post-stage Photoshop and other images There are some restrictions when dealing with group photos generated by software in different places. For example, there are problems such as incorrect light and shadow of characters and improper movements.
发明内容Contents of the invention
本发明实施例的一个目的旨在提供一种合影照片生成方法及其装置、移动终端，其解决了现有合影照片生成时缺乏互动,合成的照片图像质量低的技术问题。An object of an embodiment of the present invention is to provide a group photo generation method and its device, and a mobile terminal, which solve the existing technical problems of lack of interaction when generating group photo and low image quality of the synthesized photo.
为解决上述技术问题，本发明实施例提供以下技术方案：In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:
在第一方面，本发明实施例公开一种合影照片生成方法。所述方法包括：向接收方发送网络连接请求；获取所述接收方的第一目标3D模型及包含所述发送方的第一背景照片；或者，获取所述接收方的第二背景照片及包含所述发送方的第二目标3D模型；根据所述第一3D模型和所述第一背景照片，或者，所述第二3D模型和所述第二背景照片，生成包含所述发送方和所述接收方的合影照片。In the first aspect, the embodiment of the present invention discloses a method for generating a group photo. The method includes: sending a network connection request to the receiving party; acquiring the first target 3D model of the receiving party and including the first background photo of the sending party; or obtaining the second background photo of the receiving party and including The second target 3D model of the sender; according to the first 3D model and the first background photo, or the second 3D model and the second background photo, generate a A group photo of the recipient.
可选地，所述网络连接请求包括视频数据连接请求；所述获取所述接收方的第一目标3D模型，具体包括：在所述视频数据连接请求成功时，根据所述视频数据连接请求获得的视频图像信息，生成所述接收方的第一3D模型；将所述第一3D模型作为所述第一目标3D模型输出。Optionally, the network connection request includes a video data connection request; the acquiring the first target 3D model of the recipient specifically includes: when the video data connection request is successful, obtaining the 3D model according to the video data connection request generating a first 3D model of the receiver; and outputting the first 3D model as the first target 3D model.
可选地，所述网络连接请求包括图片数据连接请求，所述获取所述接收方的第一目标3D模型，具体包括：在所述图片数据连接请求成功时，根据所述图片数据连接请求获得3D模型的图片信息；将所述3D模型的图片信息作为所述接收方的第一目标3D模型输出。Optionally, the network connection request includes a picture data connection request, and the acquiring the first target 3D model of the recipient specifically includes: when the picture data connection request succeeds, obtaining the 3D model according to the picture data connection request The picture information of the 3D model; outputting the picture information of the 3D model as the first target 3D model of the receiver.
可选地，所述方法还包括：在所述网络连接请求未成功时，从预设模型库中选择一个所述接收方的第二3D模型；将所述第二3D模型作为所述第一目标3D模型输出。Optionally, the method further includes: when the network connection request is unsuccessful, selecting a second 3D model of the recipient from a preset model library; using the second 3D model as the first Target 3D model output.
可选地，所述预设模型库包括若干个所述接收方的第二3D模型，所述若干个所述接收方的第二3D模型互不相同。Optionally, the preset model library includes several second 3D models of the recipient, and the several second 3D models of the recipient are different from each other.
可选地，所述获取所述接收方的第二背景照片及包含所述发送方的第二目标3D模型，具体包括：Optionally, the acquiring the second background photo of the receiver and the second target 3D model including the sender specifically includes:
在所述网络连接请求成功时，通过所述网络连接获取所述接收方的第二背景照片；根据所述第二背景照片，实时生成包含所述发送方的第二目标3D模型。When the network connection request is successful, obtain a second background photo of the receiver through the network connection; generate a second target 3D model including the sender in real time according to the second background photo.
可选地，所述获取所述接收方的第二背景照片及包含所述发送方的第二目标3D模型，具体包括：Optionally, the acquiring the second background photo of the receiver and the second target 3D model including the sender specifically includes:
在所述网络连接请求成功时，通过所述网络连接获取所述接收方的第二背景照片；根据所述第二背景照片，在预设模型库中获取包含所述发送方的第二目标3D模型When the network connection request is successful, obtain a second background photo of the receiver through the network connection; according to the second background photo, obtain a second target 3D containing the sender in a preset model library Model
可选地，所述获取所述接收方的第一目标3D模型,还包括：生成初始3D模型；接收姿态调整指令；根据所述姿态调整指令，调整所述初始3D模型的姿态；根据调整后的初始3D模型的姿态，输出所述接收方的第一目标3D模型。Optionally, the acquiring the first target 3D model of the recipient further includes: generating an initial 3D model; receiving a posture adjustment instruction; adjusting the posture of the initial 3D model according to the posture adjustment instruction; adjusting the posture of the initial 3D model according to the adjusted The pose of the initial 3D model, outputting the receiver's first target 3D model.
可选地，所述姿态调整指令包括角度旋转指令和/或动作调整指令；所述根据所述姿态调整指令，调整所述初始3D模型的姿态，具体包括：根据所述角度旋转指令，调整所述接收方的初始3D模型的摆放角度和/或根据所述动作调整指令，调整所述接收方的初始3D模型的动作姿势。Optionally, the posture adjustment instruction includes an angle rotation instruction and/or an action adjustment instruction; the adjusting the posture of the initial 3D model according to the posture adjustment instruction specifically includes: adjusting the posture of the initial 3D model according to the angle rotation instruction. Adjust the position angle of the initial 3D model of the recipient and/or adjust the action posture of the initial 3D model of the recipient according to the action adjustment instruction.
在第二方面，本发明实施例提供一种合影照片生成方法，包括：接收来自发送方的网络连接请求；获取所述接收方的第一目标3D模型及包含所述发送方的第一背景照片；或者，获取所述发送方的第二背景照片及包含所述接收方的第二目标3D模型；根据所述第一3D模型和所述第一背景照片，或者，所述第二3D模型和所述第二背景照片，生成包含所述发送方和所述接收方的合影照片。In a second aspect, an embodiment of the present invention provides a method for generating a group photo, including: receiving a network connection request from a sender; obtaining a first target 3D model of the receiver and a first background photo containing the sender ; Or, acquire the second background photo of the sender and the second target 3D model including the receiver; according to the first 3D model and the first background photo, or, the second 3D model and The second background photo generates a group photo containing the sender and the receiver.
在第三方面，本发明实施例提供一种合影照片生成装置，包括：发送模块，用于向接收方发送网络连接请求；获取模块，用于获取所述接收方的第一目标3D模型及包含所述发送方的第一背景照片；或者，获取所述接收方的第二背景照片及包含所述发送方的第二目标3D模型；合影生成模块，用于根据所述第一3D模型和所述第一背景照片，或者，所述第二3D模型和所述第二背景照片，生成包含所述发送方和所述接收方的合影照片。In a third aspect, an embodiment of the present invention provides a device for generating a group photo, including: a sending module, configured to send a network connection request to the receiver; an acquisition module, configured to acquire the first target 3D model of the receiver and the The first background photo of the sender; or, obtain the second background photo of the receiver and the second target 3D model containing the sender; a group photo generation module, used for according to the first 3D model and the The first background photo, or the second 3D model and the second background photo to generate a group photo containing the sender and the receiver.
可选地，所述网络连接请求包括视频数据连接请求；所述获取模块具体用于：在所述视频数据连接请求成功时，根据所述视频数据连接请求获得的视频图像信息，生成所述接收方的第一3D模型；将所述第一3D模型作为所述第一目标3D模型输出。Optionally, the network connection request includes a video data connection request; the obtaining module is specifically configured to: when the video data connection request is successful, generate the received A first 3D model of a party; outputting the first 3D model as the first target 3D model.
可选地，所述网络连接请求包括图片数据连接请求；所述获取模块具体用于：在所述图片数据连接请求成功时，根据所述图片数据连接请求获得3D模型的图片信息；将所述3D模型的图片信息作为所述接收方的第一目标3D模型输出。Optionally, the network connection request includes a picture data connection request; the obtaining module is specifically configured to: when the picture data connection request succeeds, obtain the picture information of the 3D model according to the picture data connection request; The picture information of the 3D model is output as the first target 3D model of the receiver.
可选地，所述装置还包括：第一选择模块，用于在所述网络连接请求未成功时，从预设模型库中选择一个所述接收方的第二3D模型并将所述第二3D模型作为所述第一目标3D模型输出。Optionally, the device further includes: a first selection module, configured to select a second 3D model of the recipient from a preset model library and store the second 3D model when the network connection request is unsuccessful. A 3D model is output as the first target 3D model.
可选地，所述预设模型库包括若干个所述接收方的第二3D模型，所述若干个所述接收方的第二3D模型互不相同。Optionally, the preset model library includes several second 3D models of the recipient, and the several second 3D models of the recipient are different from each other.
可选地，所述获取模块具体用于：在所述网络连接请求成功时，根据所述网络连接请求获得的图像信息，获取所述第二接收方的第二背景照片；根据所述获取的第二背景照片，实时生成所述发送方的第二目标3D模型。Optionally, the acquiring module is specifically configured to: when the network connection request is successful, acquire the second background photo of the second recipient according to the image information obtained in the network connection request; A second background photo, generating a second target 3D model of the sender in real time.
可选地，所述装置还包括：第二选择模块，用于根据所述第二背景照片，在预设模型库中获取包含所述发送方的第二目标3D模型。Optionally, the device further includes: a second selection module, configured to acquire a second target 3D model including the sender from a preset model library according to the second background photo.
可选地，所述获取模块包括：模型生成单元，用于基于所述图像信息,生成初始3D模型；指令接收单元，用于接收姿态调整指令；姿态调整单元，用于根据所述姿态调整指令，调整所述初始3D模型的姿态；输出单元，根据调整后的初始3D模型的姿态，输出所述接收方的第一目标3D模型。Optionally, the acquiring module includes: a model generation unit, configured to generate an initial 3D model based on the image information; an instruction receiving unit, configured to receive an attitude adjustment instruction; an attitude adjustment unit, configured to adjust the instruction according to the attitude , adjusting the posture of the initial 3D model; the output unit is configured to output the first target 3D model of the receiver according to the adjusted posture of the initial 3D model.
可选地，所述姿态调整指令包括角度旋转指令和/或动作调整指令；所述姿态调整单元具体用于：根据所述角度旋转指令，调整所述接收方的初始3D模型的摆放角度和/或根据所述动作调整指令，调整所述接收方的初始3D模型的动作姿势。Optionally, the posture adjustment instruction includes an angle rotation instruction and/or an action adjustment instruction; the posture adjustment unit is specifically configured to: according to the angle rotation instruction, adjust the placement angle and position of the initial 3D model of the receiver. /or adjust the action posture of the initial 3D model of the recipient according to the action adjustment instruction.
在第四方面，本发明实施例提供一种移动终端，所述移动终端包括：至少一个处理器；以及与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够用于执行上述任一项所述的合影照片生成方法。In the fourth aspect, an embodiment of the present invention provides a mobile terminal, the mobile terminal includes: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be used by the Instructions executed by at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can be used to execute the group photo generation method described in any one of the above.
在第五方面，本发明实施例提供一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使移动终端能够执行如上任一项所述的合影照片生成方法。In the fifth aspect, the embodiment of the present invention provides a non-volatile computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable the mobile terminal to execute such as The group photo generation method described in any one of the above.
本发明实施例提供的合影照片生成方法，通过建立发送方和接收方双方之间的通信连接，实时生成接收方第一目标3D模型或者发送方的第二目标3D模型。然后配合第一背景照片或者第二背景照片，合成最终的合影照片。The group photo generation method provided by the embodiment of the present invention generates a 3D model of the first target of the receiver or a 3D model of the second target of the sender in real time by establishing a communication connection between the sender and the receiver. Then cooperate with the first background photo or the second background photo to synthesize the final group photo.
通过这样的方式一方面能够通过发送方和接收方之间建立的网络通信连接，确保双方之间充分的沟通交流，使得实时生成的第一目标3D模型或者第二目标3D模型能够与背景照片更为贴近。另一方面，由于采用的是建立人物3D模型的方式进行合影，其相对于二维平面照片更真实和立体，可实现无抠图痕迹的合影，获得的合影照片更真实、质量更高。In this way, on the one hand, the network communication connection established between the sender and the receiver can ensure sufficient communication between the two parties, so that the real-time generated first 3D model of the target or the second 3D model of the target can be more closely aligned with the background photo. for closeness. On the other hand, because the 3D model of the characters is used to take group photos, it is more realistic and three-dimensional than two-dimensional flat photos, and can realize group photos without matting traces, and the obtained group photos are more real and of higher quality.
附图说明Description of drawings
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。One or more embodiments are exemplified by the pictures in the corresponding drawings, and these exemplifications do not constitute a limitation to the embodiments. Elements with the same reference numerals in the drawings represent similar elements. Unless otherwise stated, the drawings in the drawings are not limited to scale.
图1是本发明实施例提供的一种合照应用场景示意图；Fig. 1 is a schematic diagram of a group photo application scenario provided by an embodiment of the present invention;
图2是本发明实施例提供的一种合影照片生成方法流程示意图；Fig. 2 is a schematic flowchart of a method for generating a group photo provided by an embodiment of the present invention;
图3是本发明另一实施例提供的一种合影照片生成方法流程示意图；Fig. 3 is a schematic flowchart of a method for generating a group photo according to another embodiment of the present invention;
图4本发明实施例提供的一种合影照片生成装置的结构示意图；Fig. 4 is a schematic structural diagram of a group photo generation device provided by an embodiment of the present invention;
图5本发明一实施例提供的第一输出模块的结构示意图；FIG. 5 is a schematic structural diagram of a first output module provided by an embodiment of the present invention;
图6是本发明实施例提供一种移动终端的结构示意图。Fig. 6 is a schematic structural diagram of a mobile terminal provided by an embodiment of the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
请参阅图1，图1是本发明实施例提供的合影照片生成方法的应用环境。如图1所示，该应用环境100包括以下元素：用户10和移动终端20。Please refer to FIG. 1 . FIG. 1 is an application environment of a method for generating a group photo provided by an embodiment of the present invention. As shown in FIG. 1 , the application environment 100 includes the following elements: a user 10 and a mobile terminal 20 .
用户10可以为任何合适数量的，具有相同或者相近操作行为的群体，例如家庭、工作组或者个人。每个用户10拥有或者对应一个或者多个移动终端20。Users 10 may be any suitable number of groups with the same or similar operation behaviors, such as families, work groups or individuals. Each user 10 owns or corresponds to one or more mobile terminals 20 .
移动终端20可以是任何合适类型的，具有用户交互装置和运算能力、处理能力的智能移动终端，例如：便携式电话、智能电话、平板电脑、笔记本、智能可穿戴设备(智能手表)、数字广播终端及个人数字助理(PAD)等等。The mobile terminal 20 can be any suitable type of intelligent mobile terminal with user interaction means and computing power and processing power, such as: portable phone, smart phone, tablet computer, notebook, smart wearable device (smart watch), digital broadcasting terminal And personal digital assistant (PAD) and so on.
用户10可以通过任何合适类型的，一种或者多种用户交互装置与拥有或者对应的移动终端20进行交互，例如键盘、遥控器或者触摸屏等，用户10具体可以基于上述交互装置对移动终端20进行操作以实现用户意图。The user 10 can interact with the owned or corresponding mobile terminal 20 through any suitable type, one or more user interaction devices, such as a keyboard, a remote control or a touch screen, etc., and the user 10 can specifically interact with the mobile terminal 20 based on the above-mentioned interaction device. Actions to fulfill user intent.
惯常的，在移动终端20中，可以基于上述交互装置，并且基于安装于移动终端20上的应用与其他移动终端建立相应的联系，例如，建立视频连接、建立通话连接，在建立视频连接、通话连接等时，移动终端20可以作为发送方，主动请求建立上述连接。也可以作为接收方，接收这些请求并许可建立连接。Conventionally, in the mobile terminal 20, it is possible to establish corresponding contacts with other mobile terminals based on the above-mentioned interactive means and based on the applications installed on the mobile terminal 20, for example, establish a video connection, establish a call connection, and establish a video connection, call When connecting, etc., the mobile terminal 20 may act as a sender and actively request to establish the above connection. It can also act as a receiver, accepting these requests and allowing the connection to be established.
用户10在使用移动终端20的过程中，可以基于上述交互装置，完成相应的例如拍照，拼图等功能，用以实现用户意图。其中，移动终端20在完成相应的例如拍照，拼图等功能时，能够支持多种模式的图像采集，例如支持“照片”“视频”“全景”“三维”等模式的图像采集。进一步的，“全景”和“三维”模式的图像采集，需满足基于目标物不同角度的多次采集，以达到采集后的图像满足“全景”和“三维”的视觉效果。During the process of using the mobile terminal 20, the user 10 can complete corresponding functions such as taking pictures and making puzzles based on the above-mentioned interaction means, so as to realize the user's intention. Wherein, when the mobile terminal 20 completes corresponding functions such as taking pictures and making collages, it can support multiple modes of image collection, such as supporting image collection in modes such as "photo", "video", "panorama", and "3D". Furthermore, the image acquisition in the "panoramic" and "three-dimensional" modes needs to meet multiple acquisitions based on different angles of the target, so as to achieve the "panoramic" and "three-dimensional" visual effects of the collected images.
移动终端20还可以进一步对上述模式的图像进行编辑处理，上述编辑处理包括但不限于：从“全景”模式包含的素材中提取任一目标素材；从“三维”模式包含的素材中提取任一目标素材等，以将经过编辑后获得的素材加至背景照片中，合成用户10所需要的目标照片。The mobile terminal 20 can also further edit the images in the above-mentioned modes. The above-mentioned editing processes include but are not limited to: extracting any target material from the materials contained in the "panorama" mode; extracting any target material from the materials contained in the "three-dimensional" mode. target material, etc., to add the edited material to the background photo to synthesize the target photo required by the user 10.
此处的背景照片包括但不限于指：存储在移动终端20中的照片、截图等图像信息或者应用移动终端的图像采集应用拍摄的平面照片。The background photos here include but are not limited to: image information such as photos and screenshots stored in the mobile terminal 20 , or plane photos taken with an image acquisition application of the mobile terminal.
需要说明的是，上述基于移动终端20对图像的采集和对图像的处理是相互独立的部分，既可以是移动终端20某一应用全部完成，也可以是移动终端20上具有采集图像功能的应用和具有图像处理功能的应用相互配合完成，还可以是移动终端20通过网络等数据通信方式，直接获取外部设备的图像素材。It should be noted that the above-mentioned collection of images based on the mobile terminal 20 and the processing of the images are independent parts, which can be completed by a certain application of the mobile terminal 20, or can be an application on the mobile terminal 20 that has the function of collecting images. It is completed in cooperation with an application having an image processing function, and the mobile terminal 20 may also directly obtain the image material of an external device through a data communication method such as a network.
如图1所示，用户10可以包括至少两个。相对应地，每个用户10都拥有对应的移动终端20。用户10可以使用移动终端20，通过无线网络(例如蜂窝网络)等，与其他用户的移动终端20建立实时的通信连接。基于该实时的通信连接，两个移动终端20之间可以向对方传输相应的信息，用以实现用户10之间的实时信息交流，例如实现语音通话或者视频通话等。As shown in FIG. 1, users 10 may include at least two. Correspondingly, each user 10 has a corresponding mobile terminal 20 . The user 10 can use the mobile terminal 20 to establish a real-time communication connection with other users' mobile terminals 20 through a wireless network (such as a cellular network). Based on the real-time communication connection, the two mobile terminals 20 can transmit corresponding information to each other, so as to realize real-time information exchange between users 10, such as realizing voice call or video call.
在本实施例中，为陈述简便，将发起网络连接请求，请求建立双方通信连接的一方称为发送方。将接受网络连接请求的一方称为接收方。应当说明的是，接收方与发送方仅用于表示用户10在特定的通信连接中的角色。同一个用户10在不同的通信连接中，可以作为发送方，也可以作为接收方。In this embodiment, for simplicity of presentation, the party that initiates a network connection request and requests to establish a communication connection between the two parties is referred to as the sender. A party that accepts a network connection request is called a receiver. It should be noted that the receiver and sender are only used to represent the role of the user 10 in a specific communication connection. The same user 10 can be a sender or a receiver in different communication connections.
在图1所示的应用环境中，移动终端20可以作为发送方完成下述方法实施例中的所有步骤，以实现生成与接收方之间的合影照片，使获得的合影照片具有更好的质量和真实性。In the application environment shown in FIG. 1, the mobile terminal 20 can complete all the steps in the following method embodiments as the sender, so as to realize the generation of group photo with the receiver, so that the obtained group photo has better quality and authenticity.
图1所示的应用环境中，移动终端20也可以作为接收方完成下述方法实施例中的一个或和多个步骤，以实现生成与发送方之间的合影照片，使获得的合影照片具有更好的质量和真实性。In the application environment shown in FIG. 1 , the mobile terminal 20 can also complete one or more steps in the following method embodiments as the receiver, so as to realize the generation of a group photo with the sender, so that the obtained group photo has Better quality and authenticity.
图2是本发明实施例提供的一种应用于发送方移动终端，实现的合影照片生成方法流程示意图。如图2所示，该合影照片生成方法200包括：Fig. 2 is a schematic flowchart of a method for generating a group photo, which is applied to the sender's mobile terminal and implemented according to an embodiment of the present invention. As shown in Figure 2, the group photo generation method 200 includes:
步骤21、向接收方发送网络连接请求。Step 21, sending a network connection request to the receiver.
此处所指的“接收方”为移动终端的发送方在完成拍照、合影等功能时，所需要与之建立关系的联系人。通常接收方与发送方之间具有一定的身份关系，例如亲人，同事，朋友等身份关系。The "receiver" referred to here is the contact person with whom the sender of the mobile terminal needs to establish a relationship when completing functions such as taking pictures and group photos. Usually there is a certain identity relationship between the receiver and the sender, such as relatives, colleagues, friends and other identity relationships.
基于不同的实际需要，发送方可以选择相应的联系人作为接收方以发送网络连接请求。该“网络连接请求”为发送方移动终端与接收方移动终端之间建立的，能够进行视频或者图像等音视频数据传输的通信连接。其中，发送方移动终端与接收方移动终端之间可以通过合适类型的网络建立通信通道，并向对方实时传输视频图像或者图片。Based on different actual needs, the sender can select a corresponding contact as the receiver to send the network connection request. The "network connection request" is a communication connection established between the mobile terminal of the sending party and the mobile terminal of the receiving party, capable of transmitting audio and video data such as video or images. Wherein, a communication channel can be established between the mobile terminal of the sending party and the mobile terminal of the receiving party through a suitable type of network, and real-time transmission of video images or pictures to the other party.
步骤22、获取所述接收方的第一目标3D模型及包含所述发送方的第一背景照片；或者，获取所述接收方的第二背景照片及包含所述发送方的第二目标3D模型。Step 22. Obtain the first target 3D model of the receiver and the first background photo including the sender; or, acquire the second background photo of the receiver and the second target 3D model including the sender .
在发送方的移动终端与接收方的移动终端之间建立无线通信连接时，可以基于该无线通信信道，获取到对方的相关图像信息。该图像信息可以是视频图像、人物图片或者景物图片等。When a wireless communication connection is established between the mobile terminal of the sending party and the mobile terminal of the receiving party, relevant image information of the other party can be obtained based on the wireless communication channel. The image information may be a video image, a picture of a person or a picture of a scene, and the like.
例如，发送方的移动终端可以获取接收方的移动终端拍摄获得，包含接收方的图像信息，并生成对应的第一目标3D模型。接收方的移动终端也可以获取来自发送方的移动终端拍摄获得的，包含发送方的图像信息，并生成对应的第二目标3D模型。For example, the mobile terminal of the sender can obtain the photographed image information of the mobile terminal of the receiver, including the image information of the receiver, and generate a corresponding 3D model of the first target. The receiver's mobile terminal may also acquire image information including the sender's image captured by the sender's mobile terminal, and generate a corresponding second target 3D model.
当然，第一目标3D模型和第二目标3D模型均可以在任意一方的移动终端中生成，并传输到对方的移动终端中。Of course, both the first 3D model of the target and the second 3D model of the target can be generated in the mobile terminal of either party and transmitted to the mobile terminal of the other party.
又例如，发送方的移动终端将自己拍摄获得的二维图片照片提供给接收方的移动终端，作为第一背景照片使用。接收方的移动终端也可以将自己拍摄获得二维图像照片提供给发送方的移动终端，作为第二背景照片使用。For another example, the mobile terminal of the sending party provides the mobile terminal of the receiving party with a two-dimensional picture taken by itself as a first background photo. The mobile terminal of the receiving party may also provide the mobile terminal of the sending party with a photo of the two-dimensional image taken by itself as a second background photo.
步骤23、根据所述第一3D模型和所述第一背景照片，或者，所述第二3D模型和所述第二背景照片，生成包含所述发送方和所述接收方的合影照片。Step 23: Generate a group photo containing the sender and the receiver according to the first 3D model and the first background photo, or the second 3D model and the second background photo.
在一般的人物合照中，可以划分为人物和背景两部分。在本实施例中，背景照片作为最终合成的合影照片的基础，背景照片的背景作为合影照片的背景，而需要合成到背景中的人物则来自于人物的第一目标3D模型或者第二目标3D模型。In a general photo of people, it can be divided into two parts: the person and the background. In this embodiment, the background photo is used as the basis of the final composite group photo, the background of the background photo is used as the background of the group photo, and the characters that need to be synthesized into the background come from the first object 3D model or the second object 3D model of the person. Model.
该合影照片合成的素材可以有多种组合形式。例如，发送方的移动终端可以以自身摄像头拍摄的第一背景照片和来自接收方的第一目标3D模型作为合成素材，合成包含有接收方和发送方的合影照片。The materials synthesized by the group photo can have various combinations. For example, the sender's mobile terminal can use the first background photo taken by its own camera and the first target 3D model from the receiver as composite materials to synthesize a group photo containing the receiver and the sender.
或者是，发送方的移动终端还可以采用来自自身的第二目标3D模型和来自接收方的第二背景照片作为合成素材，合成包含有接收方和发送方的合影照片Or, the sender's mobile terminal can also use the second target 3D model from itself and the second background photo from the receiver as composite materials to synthesize a group photo containing the receiver and the sender
上述两种合成方式可以由用户根据实际情况的需要进行选择。在同一个无线网络通信连接过程中，也可以同时执行上述多种组合方式，合成多张不同的合影照片。The above two synthesis methods can be selected by the user according to the needs of the actual situation. During the same wireless network communication connection process, the above multiple combination methods can also be executed simultaneously to synthesize multiple different group photos.
上述实施例从发送方的角度完成获取接收方的第一目标3D模型及包含发送方的第一背景照片；或者，获取接收方的第二背景照片及包含所述发送方的第二目标3D模型这一步骤，以及完成生成包含发送方和接收方的合影照片这一步骤。The above embodiment completes the acquisition of the first target 3D model of the receiver and the first background photo including the sender from the perspective of the sender; or, acquires the second background photo of the receiver and the second target 3D model including the sender This step, and complete the step of generating a group photo of the sender and receiver.
此处需要再次强调的是，上述方法实施中的一个或者多个方法步骤也可以在接收方完成，例如，用户佩戴一智能可穿戴设备,如智能手表，则在智能手表接收到发送方的网络连接请求之后，可以获取第一目标3D模型及包含发送方的第一背景照片；或者，获取第二背景照片及包含发送方的第二目标3D模型；智能手表然后根据第一3D模型和第一背景照片，或者，根据第二3D模型和第二背景照片，生成包含发送方和接收方的合影照片。What needs to be emphasized here is that one or more method steps in the implementation of the above method can also be completed on the receiving side. For example, if the user wears a smart wearable device, such as a smart watch, the smart watch receives the network After the connection request, the first target 3D model and the first background photo containing the sender can be obtained; or, the second background photo and the second target 3D model containing the sender can be obtained; the smart watch then uses the first 3D model and the first A background photo, or, according to the second 3D model and the second background photo, generate a group photo containing the sender and the receiver.
以下结合具体应用实例，详细描述移动终端如何执行上述方法实施例中的步骤。The following describes in detail how the mobile terminal executes the steps in the foregoing method embodiments in conjunction with specific application examples.
例如，小红外出出差，暂时与男友处于异地状态，路途中偶然见到一处美景想与男友合照，则小红可以选择先与该美景合影，并将该合影的美景照片作为背景照片应用于与男友的合影照片中。For example, when Xiaohong is on a business trip and is temporarily in a different place with her boyfriend, she happens to see a beautiful scenery on the way and wants to take a photo with her boyfriend. In a photo with her boyfriend.
小红进一步打开手机相机(发送方移动终端)，选择接收方为“男友”，并且向男友发送视频数据的连接请求。在男友成功接收(接收方移动终端)该视频数据连接时，男友的手机相机开启，并将拍摄得到的包含男友的视频图像传输至小红的手机中。其中，两人可通过双方的手机在屏幕上进行互动，以帮助男友摆出符合背景照片中的姿势，并且获取该相应姿势的视频图像；小红的手机进而可以通过相应的3D模型构建方法，通过这些获取得到的视频图像采集男友的三维立体参数，从而构建生成与男友对应的3D模型，并将该3D模型作为第一目标3D模型，应用于合影照片中。Xiaohong further turns on the mobile phone camera (the sender's mobile terminal), selects the receiver as "boyfriend", and sends a video data connection request to her boyfriend. When the boyfriend successfully receives (receiver's mobile terminal) the video data connection, the camera of the boyfriend's mobile phone is turned on, and the captured video image containing the boyfriend is transmitted to Xiaohong's mobile phone. Among them, the two can interact on the screen through their mobile phones to help her boyfriend pose in a pose that matches the background photo, and obtain a video image of the corresponding pose; Xiaohong's mobile phone can then use the corresponding 3D model construction method, The three-dimensional parameters of the boyfriend are collected through the acquired video images, thereby constructing and generating a 3D model corresponding to the boyfriend, and using the 3D model as the first target 3D model, and applying it to the group photo.
实际的合成过程可以是：首先将第一目标3D模型或者第二目标3D模型进行平面取样，获得相应的平面图像后，将接收方的人物平面图像加入到背景照片中，从而最终形成包含接收方和发送方的合影照片。The actual synthesis process can be as follows: firstly, the first target 3D model or the second target 3D model is plane-sampled, and after obtaining the corresponding plane image, the plane image of the person of the receiver is added to the background photo, so as to finally form a 3D model containing the receiver Take a photo with the sender.
例如，在获得包含小红的背景照片和男友的3D模型之后，将男友的3D模型进行平面取样，获得男友的平面图像，并且将该平面图像加入到背景照片中，从而最终生成包含小红和男友的合影照片。For example, after obtaining the background photo containing Xiaohong and her boyfriend's 3D model, the boyfriend's 3D model is sampled to obtain a planar image of her boyfriend, and the planar image is added to the background photo to finally generate a model containing Xiaohong and her boyfriend. A photo of the boyfriend.
在另一些应用场景中，本发明实施例提供的合影照片生成方法还可以应用于多人合影的场景。例如，在确定了接收方为父亲的目标3D模型，以及包含发送方和母亲的合照作为背景照片以后，发送方可以选择在背景照片的合适位置，加入由父亲的3D模型产生的图像，合成最终包括了父亲、母亲以及发送方三人的合影照片。In other application scenarios, the method for generating a group photo provided by the embodiment of the present invention may also be applied to a scene where multiple people take a group photo. For example, after determining that the recipient is the target 3D model of the father, and including the photo of the sender and mother as the background photo, the sender can choose to add the image generated by the father's 3D model to the appropriate position of the background photo to synthesize the final Including a group photo of the father, mother and the sender.
在本发明实施例中，以建立网络连接的方式，可以实时生成3D模型以及挑选背景照片，并根据该3D模型和背景照片来合成最终的合影照片。这样的合影照片生成方式一方面能够实现发送方和接收方之间的充分沟通交流，使得实时生成的第一目标3D模型与第一背景照片或者第二目标3D模型与第二背景照片之间更为贴近。另一方面，由于3D模型相对于二维平面照片更真实和立体，可实现无抠图痕迹的合影，使得利用第一目标3D模型或者第二目标3D模型生成的合影照片更真实，合影照片质量更高。In the embodiment of the present invention, by establishing a network connection, a 3D model and a background photo can be generated in real time, and a final group photo can be synthesized according to the 3D model and the background photo. On the one hand, such a group photo generation method can realize sufficient communication between the sender and the receiver, so that the real-time generated first target 3D model and the first background photo or the second target 3D model and the second background photo are closer. for closeness. On the other hand, because the 3D model is more real and three-dimensional than the two-dimensional plane photo, it can realize the group photo without matting traces, so that the group photo generated by the first target 3D model or the second target 3D model is more realistic and the quality of the group photo is higher. higher.
在一些实施例中，根据需要获取的图像信息的不同，网络连接请求可以包括：图片数据连接请求和/或者视频数据连接请求。此处的“视频数据连接请求”为以任何合适方式通过调用接收方移动终端的摄像头所取得的请求，该请求可以依附于接收方移动终端上安装的与调用摄像头相关的应用程序完成，例如，利用微信上的视频功能、利用某一应用程序A调用相机应用程序等完成。In some embodiments, according to different image information to be acquired, the network connection request may include: a picture data connection request and/or a video data connection request. The "video data connection request" here is a request obtained by invoking the camera of the receiving party's mobile terminal in any suitable way, and the request can be completed by attaching to the application program installed on the receiving party's mobile terminal related to calling the camera, for example, Use the video function on WeChat, use a certain application A to call the camera application, etc. to complete.
此处的“图片数据连接请求”为以任何合适方式建立的图片传输请求，该图片传输从接收方移动终端获得。The "picture data connection request" here is a picture transmission request established in any suitable way, and the picture transmission is obtained from the receiver's mobile terminal.
相对应地，在步骤22中具体可以根据网络连接请求而执行不同的步骤以输出第一目标3D模型。Correspondingly, in step 22, different steps may be executed specifically according to the network connection request to output the first target 3D model.
例如，当网络连接请求为视频数据连接请求，并且视频数据连接请求成功时，发送方的移动终端可以根据所述视频数据连接请求获得的视频图像信息，生成所述接收方的第一3D模型。然后，将所述第一3D模型作为所述第一目标3D模型输出。For example, when the network connection request is a video data connection request, and the video data connection request is successful, the sender's mobile terminal can generate the first 3D model of the receiver according to the video image information obtained by the video data connection request. Then, output the first 3D model as the first target 3D model.
在本实施例中，发送方和接收方使用的移动终端的摄像机均会开启，分别用于拍摄相应的图像，从而实现双方之间的视频数据通信连接。其中，发送方使用的移动终端拍摄的图像可以显示在接收方使用的移动终端上。接收方使用的移动终端拍摄的图像则显示在接收方使用的移动终端上。In this embodiment, the cameras of the mobile terminals used by the sender and the receiver are both turned on, and are respectively used to capture corresponding images, so as to realize the video data communication connection between the two parties. Wherein, the image taken by the mobile terminal used by the sender can be displayed on the mobile terminal used by the receiver. The images taken by the mobile terminal used by the receiver are then displayed on the mobile terminal used by the receiver.
此处的视频图像具体指通过接收方的移动终端拍摄获得的图像。其在视频数据过程中，传输至发送方的移动终端中。发送方的移动终端可以通过相应的3D模型构建方法，通过这些视频图像采集接收方的三维立体参数，从而构建生成与接收方对应的第一3D模型。在本实施例中，该3D模型具体可以通过多种不同的软件或者应用生成，例如3DMax。The video image here specifically refers to an image captured by the receiver's mobile terminal. It is transmitted to the sender's mobile terminal during the video data process. The mobile terminal of the sender can use the corresponding 3D model building method to collect the 3D parameters of the receiver through these video images, so as to construct and generate the first 3D model corresponding to the receiver. In this embodiment, the 3D model can be specifically generated by various software or applications, such as 3DMax.
在实际操作使用过程中，发送方和接收方之间可以通过语音交流，从而令接收方摆出不同的动作和造型。然后，接收方使用自己的移动终端拍摄多个符合要求的，包含有接收方的图像。发送方的移动终端便可以根据这些图像信息，快速生成接收方的第一3D模型并作为第一目标3D模型输出。During the actual operation, the sender and the receiver can communicate through voice, so that the receiver can pose different actions and poses. Then, the receiving party uses its own mobile terminal to shoot a plurality of images that meet the requirements and include the receiving party. The mobile terminal of the sender can quickly generate the first 3D model of the receiver according to the image information and output it as the first target 3D model.
该3D模型与惯常拍摄获得的平面图像不相同的是，在实际合影照片生成过程中，移动终端可以通过以该3D模型为基础，截取或者获得接收方的多个不同视角上拍摄获得的平面图像。The difference between this 3D model and the plane images obtained by usual shooting is that during the actual generation of group photos, the mobile terminal can intercept or obtain the plane images obtained by shooting from multiple different angles of view of the receiver based on the 3D model .
该第一3D模型由于是通过视频数据连接方式，由发送方和接收方实时交流以后形成的，因此，能够很好的与当前的场景契合。在本实施例中，将该实时生成的3D模型作为第一3D模型，最终用于合影照片中的第一目标3D模型中，而不需要进行修饰、调整，以与背景照片中的场景契合，即可满足合成的合影照片较为自然，整体性好。在一些实施例中，根据发送方的喜好，也可以对该生成的3D模型进行相应的修饰、调整等步骤，以得到第一3D模型，并作为最终应用于合影照片中的第一目标3D模型，应用于后期的合影照片中。Since the first 3D model is formed after real-time communication between the sender and the receiver through the video data connection, it can fit well with the current scene. In this embodiment, the real-time generated 3D model is used as the first 3D model, and is finally used in the first target 3D model in the group photo without modification or adjustment to match the scene in the background photo. The group photo that can be satisfied with the synthesis is more natural and has good integrity. In some embodiments, according to the preference of the sender, the generated 3D model can also be modified, adjusted and other steps to obtain the first 3D model, and used as the first target 3D model finally applied in the group photo , which will be applied to the group photo later.
在本实施例中，该第一目标3D模型是发送方和接收方之间经过充分交流沟通后获得的3D模型。因此，这样的3D模型能够更贴近背景照片的需求，也模拟了双方在合影过程中的沟通交流过程，提高了生成的合影照片的真实性和质量。In this embodiment, the first target 3D model is a 3D model obtained after sufficient communication between the sender and the receiver. Therefore, such a 3D model can be closer to the requirements of the background photo, and also simulates the communication process between the two parties during the group photo, improving the authenticity and quality of the generated group photo.
当然，第二目标3D模型也可以采用类似的方式，由发送方基于来自接收方的背景照片对应生成。但是，由于第二目标3D模型为发送方的人物3D模型。因此，发送方的移动终端只需要在接收到背景照片时即可生成第二目标3D模型，而不限于在视频数据连接请求成功时生成第二目标3D模型。Of course, the second target 3D model can also be generated in a similar manner by the sender based on the background photo from the receiver. However, since the second target 3D model is the sender's character 3D model. Therefore, the sender's mobile terminal only needs to generate the second target 3D model when receiving the background photo, and is not limited to generating the second target 3D model when the video data connection request succeeds.
在另一些实施例中，当网络连接请求为图片数据连接请求，并且连接请求成功时，发送方可以接收来自于接收方的3D模型的图片信息，该3D模型的图片信息可以是合成接收方的3D模型的相关图片信息。接收方可以基于该3D模型的图片信息输出包含接收方的第一目标3D模型。In some other embodiments, when the network connection request is a picture data connection request, and the connection request is successful, the sender may receive the picture information of the 3D model from the receiver, and the picture information of the 3D model may be synthesized from the receiver's 3D model related picture information. The receiving party may output the first target 3D model including the receiving party based on the picture information of the 3D model.
当然，第二目标3D模型也可以采用类似的方式，由发送方基于来自接收方的背景照片对应生成。但是，由于第二目标3D模型为发送方的人物3D模型。因此，发送方的移动终端只需要在接收到背景照片时即可生成第二目标3D模型，而不限于在图片数据连接请求成功时生成第二目标3D模型。Of course, the second target 3D model can also be generated in a similar manner by the sender based on the background photo from the receiver. However, since the second target 3D model is the sender's character 3D model. Therefore, the sender's mobile terminal only needs to generate the second target 3D model when receiving the background photo, and is not limited to generating the second target 3D model when the image data connection request succeeds.
而在发送方与接收方建立网络数据连接时，还可能存在这样的情况：接收方因为个人原因，无法及时响应移动终端以建立网络数据连接。此时发送方可以选择从预设模型库中选择一个所述接收方的第二3D模型。然后，将所述第二3D模型作为所述第一目标3D模型输出。When the sender establishes a network data connection with the receiver, there may also be such a situation: the receiver cannot respond to the mobile terminal in time to establish the network data connection due to personal reasons. At this time, the sender may choose to select a second 3D model of the receiver from the preset model library. Then, output the second 3D model as the first target 3D model.
上述“预设模型库”可以是以任何合适的方式存储于云端或者本地的数据库，发送方移动终端例如，可以在网络连接的情况下从云端获取第二3D模型，还可以例如，在不建立网络连接的情况下从本地获取第二3D模型。每个预设模型库与一个接收方对应，其中存储有若干个第二3D模型。在具有相应的获取权限的情况下，移动终端可以获取预设模型库中的第二3D模型。The above-mentioned "preset model library" can be stored in the cloud or a local database in any suitable manner. For example, the sender mobile terminal can obtain the second 3D model from the cloud under the condition of network connection, or, for example, without establishing The second 3D model is obtained locally under the condition of network connection. Each preset model library corresponds to a receiver, and several second 3D models are stored therein. In the case of having the corresponding acquisition authority, the mobile terminal can acquire the second 3D model in the preset model library.
在本实施例中，该第一3D模型和第二3D模型均是指同一个接收方的3D模型。使用第一和第二仅用于区分接收方的3D模型的来源。第一3D模型是指实时生成的3D模型。而第二3D模型则是指存储在数据库内的3D模型。当然，该第一3D模型也可以保存到该预设模型库中，从而成为第二3D模型供选择使用。In this embodiment, the first 3D model and the second 3D model both refer to the 3D model of the same recipient. Use first and second only to distinguish the source of the recipient's 3D model. The first 3D model refers to a 3D model generated in real time. The second 3D model refers to the 3D model stored in the database. Of course, the first 3D model can also be saved in the preset model library, so as to become the second 3D model for optional use.
具体的，在预设模型库中的第二3D模型均互不相同。3D模型互不相同是指3D模型的外形或者外表不相同，存在区别。例如，对于同一个接收方来说，可以具有穿着短袖衣服的第二3D模型，也可以具有穿着长袖衣服的第二3D模型。Specifically, the second 3D models in the preset model library are all different from each other. The different 3D models mean that the shapes or appearances of the 3D models are different, and there are differences. For example, for the same recipient, there may be a second 3D model wearing short-sleeved clothing, and a second 3D model wearing long-sleeved clothing.
第二3D模型具体的外表或者外形是由接收方在建立3D模型时的情况所决定。当然，为了更好的满足发送方的选择需求，预设模型库中可以包括多种第二3D模型。The specific appearance or shape of the second 3D model is determined by the situation when the recipient creates the 3D model. Of course, in order to better meet the selection requirements of the sender, the preset model library may include multiple second 3D models.
当然，如上所述，作为发送方也会具有自己相应的预设模型库(因发送方也有可能在某些通信连接中担任接收方)。因此，发送方的移动终端也可以在使用第二背景照片时，直接从发送方自身的预设模型库中获取第二目标3D模型，完成照片的合成。Of course, as mentioned above, the sender also has its own corresponding preset model library (since the sender may also act as the receiver in some communication connections). Therefore, when using the second background photo, the sender's mobile terminal can directly acquire the second target 3D model from the sender's own preset model library to complete the synthesis of photos.
例如，小李常年在外工作，中秋佳节因工作原因未能回家，但给家里的父母妻儿规划了旅游。在家人旅游途中，进行合照时小李妻子打开相机选择接收方为“小李”，并且向小李发送视频数据的连接请求。但此时小李在公司无法参与妻子建立视频数据，则小李可以打开预设模型库内各种小李的模型，并选择与背景照片相应的模型发送至妻子的手机，以完成后续与家人的合照。For example, Xiao Li works outside the home all year round, and was unable to go home during the Mid-Autumn Festival due to work reasons, but planned a trip for his parents, wife and children at home. During the family trip, Xiao Li's wife turned on the camera and selected the receiver as "Xiao Li" when taking a group photo, and sent a video data connection request to Xiao Li. But at this time, Xiao Li cannot participate in his wife's creation of video data in the company, so Xiao Li can open various models of Xiao Li in the preset model library, and select the model corresponding to the background photo and send it to his wife's mobile phone to complete the follow-up communication with his family. photo.
一般的，为了构建完整的三维立体模型，移动终端在建立视频数据连接时拍摄的包含有接收方的图像，或者在预先构建第一3D模型，以将该接收方的第一3D模型存储于预设模型库中时，均需要从不同拍摄角度拍摄包含接收方的若干张样本图片。该样本图片具体可以是在不同拍摄角度或者不同视角，拍摄接收方所获得的图片。例如，从正前方、左侧、右侧以及正后方四个拍摄角度拍摄的图片。该样本图片是生成第一3D模型的基础数据。Generally, in order to construct a complete three-dimensional model, the mobile terminal captures an image containing the recipient when establishing a video data connection, or constructs a first 3D model in advance, so as to store the first 3D model of the recipient in the preset When setting up the model library, it is necessary to take several sample pictures including the receiver from different shooting angles. Specifically, the sample picture may be a picture obtained by shooting the receiving party at different shooting angles or different viewing angles. For example, pictures taken from four shooting angles: front, left, right, and back. The sample picture is basic data for generating the first 3D model.
当该样本图片是在建立视频通话通过实时采集得到时，该采集得到的样本图片，应当包含足够数量的，位于不同拍摄角度的样本图片，以生成完整的3D模型。完整的3D模型是指接收方在各个角度上的图像数据均是完备的，能够满足3D模型的精细度要求。When the sample picture is obtained through real-time collection when establishing a video call, the collected sample picture should include a sufficient number of sample pictures at different shooting angles to generate a complete 3D model. A complete 3D model means that the receiver's image data at all angles are complete and can meet the fineness requirements of the 3D model.
例如，某个第一3D模型的精细度要求可以是：在接收方的360°方向上，每间隔10°拍摄一张样本图片。亦即需要至少36张样本图片，每张样本图片之间的拍摄角度相差36°。当然，发送方也可以根据实际情况调整所述第一3D模型的精细度，从而降低或者升高能够生成完整的第一3D模型的判断标准。For example, the fineness requirement of a certain first 3D model may be: in the 360° direction of the receiver, take a sample picture every 10°. That is, at least 36 sample pictures are required, and the shooting angles of each sample picture differ by 36°. Of course, the sender can also adjust the fineness of the first 3D model according to the actual situation, so as to lower or raise the criterion for generating a complete first 3D model.
在所包含的所有样本图片中缺失了某个拍摄角度的样本图片时，移动终端或者用于生成3D模型的移动终端可以向发送方发出相应的提示信息，提示发送方重新进行拍摄，以确保能够采集到足够的样本图片，生成完整的3D模型。When the sample picture of a certain shooting angle is missing from all the sample pictures included, the mobile terminal or the mobile terminal used to generate the 3D model can send a corresponding prompt message to the sender, prompting the sender to take the picture again, so as to ensure that the Collect enough sample images to generate a complete 3D model.
该提示信息可以是不同类型或者不同展示方式的信息，例如提示语音或者提示文本框。发送方可以根据提示信息的指引，使用移动终端重新拍摄缺失的包含接收方的样本图片。并基于该所有的样本图片，通过拼接等方式，生成接收方的第一3D模型。具体的第一3D模型的生成过程The prompt information may be information of different types or in different display modes, such as prompt voice or prompt text box. The sender can use the mobile terminal to retake the missing sample picture containing the receiver according to the guidance of the prompt information. And based on all the sample pictures, the first 3D model of the receiving party is generated by splicing and other methods. Specific generation process of the first 3D model
为了提供更好、更真实的合影照片，在生成接收方的第一3D模型之前，移动终端还可以进一步的对3D模型进行一定的修饰或者调整以得到第一目标3D模型。当然，由于第二目标3D模型是发送方的3D模型。因此，第二目标3D模型也可以执行与上述第一目标3D模型相同的调整和修饰步骤，为陈述简便，在此不作赘述。In order to provide better and more realistic group photos, before generating the recipient's first 3D model, the mobile terminal may further modify or adjust the 3D model to obtain the first target 3D model. Of course, since the second target 3D model is the 3D model of the sender. Therefore, the second target 3D model can also perform the same adjustment and modification steps as the above-mentioned first target 3D model, which is not repeated here for the sake of simplicity.
具体的，图3是本发明另一实施例提供的一种合影照片生成方法流程示意图，上述实施例中对各步骤的解释在本实施例中同样适用，如图3所示，该方法包括：Specifically, FIG. 3 is a schematic flow chart of a method for generating a group photo according to another embodiment of the present invention. The explanations for each step in the above embodiment are also applicable in this embodiment. As shown in FIG. 3 , the method includes:
步骤31、向接收方发送网络连接请求。Step 31, sending a network connection request to the receiver.
步骤32、根据所述网络连接请求，获取所述接收方的图像信息，基于所述图像信息,生成初始3D模型。Step 32. According to the network connection request, acquire the image information of the recipient, and generate an initial 3D model based on the image information.
此处所指的初始3D模型，为根据图像信息实时生成的3D模型，没有经过发送方移动终端的任何处理。The initial 3D model referred to here is a 3D model generated in real time based on image information without any processing by the sender's mobile terminal.
步骤33、接收姿态调整指令，并根据姿态调整指令，调整初始3D模型的姿态。Step 33: Receive an attitude adjustment instruction, and adjust the attitude of the initial 3D model according to the attitude adjustment instruction.
在本实施例中，姿态调整指令是指发送方向其使用的移动终端发出的，用于表示发送方对初始3D模型进行调整或者修改意图的命令。发送方移动终端在接收到该姿态调整指令以后，可以据此对第一3D模型的姿态进行相应的调整，生成符合发送方意图的第一3D模型。当然，在实际使用过程中，发送方还可以对3D模型进行多次的修改，而不限于一次。In this embodiment, the posture adjustment instruction refers to a command sent by the sender to the mobile terminal used by the sender, which is used to indicate the sender's intention to adjust or modify the initial 3D model. After receiving the posture adjustment instruction, the sender's mobile terminal can adjust the posture of the first 3D model accordingly to generate the first 3D model that meets the intention of the sender. Of course, in actual use, the sender can modify the 3D model multiple times, not limited to one time.
在一些实施例中，该姿态调整指令也可以是由接收方发出的，对自己的初始3D模型的姿态进行调整。当然，调整的目标也可以是从预设模型库中获取的第二3D模型。In some embodiments, the pose adjustment command may also be sent by the receiver to adjust the pose of its own initial 3D model. Of course, the adjustment target may also be the second 3D model obtained from the preset model library.
步骤34、根据调整后的初始3D模型的姿态，输出所述接收方的第一目标3D模型。Step 34: Output the first target 3D model of the receiver according to the adjusted posture of the initial 3D model.
步骤35、确定包含发送方图像的第一背景照片；Step 35, determine the first background photo containing the image of the sender;
步骤36、根据第一目标3D模型和第一背景照片生成包含发送方和接收方的合影照片。Step 36: Generate a group photo containing the sender and the receiver according to the first 3D model of the target and the first background photo.
在一些实施例中，姿态调整指令具体可以包括：角度旋转指令和/或动作调整指令。In some embodiments, the posture adjustment instruction may specifically include: an angle rotation instruction and/or an action adjustment instruction.
该角度旋转指令包含了旋转角度，是指发送方希望初始3D模型从当前摆放角度旋转到目标摆放角度所需要转过的角度。例如，从当前角度，沿逆时针方向旋转90°。The angle rotation command includes the rotation angle, which refers to the angle that the sender wants the initial 3D model to rotate from the current placement angle to the target placement angle. For example, from the current angle, rotate 90° counterclockwise.
该动作调整指令包含了动作描述，是指发送方希望初始3D模型从当前的姿势调整到目标姿势所需要经过的动作。例如，父亲的初始3D模型从站立姿势，通过手臂的移动操作，改变为挥手姿势的3D模型作为第一3D模型。The action adjustment command includes an action description, which refers to the action that the sender wants the initial 3D model to undergo to adjust from the current pose to the target pose. For example, the initial 3D model of the father is changed from the standing posture to the 3D model of the waving posture through the movement operation of the arm as the first 3D model.
与上述姿态调整指令相对应的，根据所述姿态调整指令，调整初始3D模型的姿态的步骤则具体可以包括：Corresponding to the above posture adjustment instruction, according to the posture adjustment instruction, the step of adjusting the posture of the initial 3D model may specifically include:
首先，根据角度旋转指令，调整接收方的3D合照模型的摆放角度和/或根据动作调整指令，调整接收方的3D合照模型的动作姿势。Firstly, according to the angle rotation instruction, the placement angle of the recipient's 3D photo model is adjusted and/or according to the action adjustment instruction, the action posture of the recipient's 3D photo model is adjusted.
在本实施例中，将对接收方初始3D模型的调整划分为角度调整和动作姿势调整两个不同的调整方式。发送方可以通过这两种调整方式，对初始3D模型进行调整，生成多种不同的3D模型作为目标3D模型，用于合成不同的合影照片。In this embodiment, the adjustment of the receiver's initial 3D model is divided into two different adjustment modes: angle adjustment and action posture adjustment. The sender can adjust the initial 3D model through these two adjustment methods, and generate multiple different 3D models as target 3D models for synthesizing different group photos.
在合影照片的素材(即目标3D模型以及背景照片)均准备完成后，移动终端便可以据此生成符合发送方要求的合影照片。这样生成的合影照片自由度较大，发送方可以方便的通过调整初始3D模型的方式来生成不同的合影照片，而不需要进行抠图等繁琐的操作。After the material of the group photo (that is, the target 3D model and the background photo) is prepared, the mobile terminal can generate a group photo that meets the requirements of the sender. The group photos generated in this way have a greater degree of freedom, and the sender can easily generate different group photos by adjusting the initial 3D model without performing cumbersome operations such as cutouts.
本发明实施例提供的合影照片生成方法，通过生成3D模型的方式来合成最终的合影照片，一方面能够避免原有的使用Photoshop等图像处理软件需要进行抠图等繁琐的修图操作，有效的提高了合影照片的生成效率。另一方面，由于接收方使用的是3D模型，相对于平面照片，可以方便对3D模型进行例如，角度旋转、关节拖动等动作的改变，以使接收方的3D模型经过调整后的姿态与背景照片中的人物或者实物姿态相对应，将该经过调整的3D模型添加至背景照片中，生成的合影照片更自然，无抠图痕迹，这种方法有效的解决了异地合照的问题，并且能够生成更多的美照。The group photo generation method provided by the embodiment of the present invention synthesizes the final group photo by generating a 3D model. On the one hand, it can avoid the cumbersome image retouching operations such as the original use of Photoshop and other image processing software, which is effective. Improved the efficiency of group photo generation. On the other hand, since the receiver uses a 3D model, it is convenient to change the 3D model, such as angle rotation and joint dragging, so that the adjusted posture of the receiver's 3D model is consistent with The poses of the people or objects in the background photo correspond to each other. Adding the adjusted 3D model to the background photo will result in a more natural group photo without cutout traces. This method effectively solves the problem of taking photos in different places, and can Generate more beautiful photos.
应当说明的是，上述方法实施例中，为陈述简便，均以发送方的移动终端作为执行主体的角度进行描述。但步骤22以及步骤23也可以在接收方的移动终端中执行。进一步的，上述方法实施例中的步骤也可以部分在发送方的移动终端中执行，部分在接收方的移动终端中执行。本领域技术人员可以根据实际需要，将上述方法实施例中的方法步骤进行调整、替换或者整合，分配至发送方的移动终端或者接收方的移动终端中执行。It should be noted that, in the foregoing method embodiments, for the sake of simplicity, descriptions are made from the perspective of the sender's mobile terminal as the execution subject. But step 22 and step 23 can also be executed in the receiver's mobile terminal. Further, the steps in the foregoing method embodiments may also be partially executed in the mobile terminal of the sender, and partially executed in the mobile terminal of the receiver. Those skilled in the art can adjust, replace or integrate the method steps in the above method embodiments according to actual needs, and assign them to the mobile terminal of the sender or the mobile terminal of the receiver for execution.
作为本发明实施例的另一方面，本发明实施例提供一种合影照片生成装置。如图4所示，该合影照片生成装置400包括：发送模块41、获取模块42和合影生成模块43。As another aspect of the embodiment of the present invention, the embodiment of the present invention provides an apparatus for generating a group photo. As shown in FIG. 4 , the group photo generating device 400 includes: a sending module 41 , an acquiring module 42 and a group photo generating module 43 .
发送模块41用于向接收方发送网络连接请求。获取模块42，用于获取所述接收方的第一目标3D模型及包含所述发送方的第一背景照片；或者，获取所述接收方的第二背景照片及包含所述发送方的第二目标3D模型；合影生成模块43，用于根据所述第一3D模型和所述第一背景照片，或者，所述第二3D模型和所述第二背景照片，生成包含所述发送方和所述接收方的合影照片。The sending module 41 is used to send a network connection request to the receiver. The acquisition module 42 is used to acquire the first target 3D model of the receiver and the first background photo including the sender; or, acquire the second background photo of the receiver and the second background photo including the sender. Target 3D model; group photo generating module 43, configured to generate an image containing the sender and the first background photo according to the first 3D model and the first background photo, or the second 3D model and the second background photo. A group photo of the recipient.
上述合影照片生成装置,可以实时生成3D模型，并合成最终的合影照片。一方面，能够根据建立的网络连接，通过充分的沟通交流，使得实时生成的第一目标3D模型或者第二目标3D模型与第一背景照片或第二背景照片更为贴近。另一方面，由于3D模型相对于二维平面照片更真实和立体，可实现无抠图痕迹的合影，生成的合影照片更真实，合影照片质量更高。The above group photo generation device can generate a 3D model in real time and synthesize the final group photo. On the one hand, the first 3D model of the target or the second 3D model of the target generated in real time can be closer to the first background photo or the second background photo through sufficient communication according to the established network connection. On the other hand, since the 3D model is more real and three-dimensional than the two-dimensional plane photo, it can realize the group photo without matting traces, and the generated group photo is more realistic and the quality of the group photo is higher.
在一些实施例中，所述网络连接请求包括视频数据连接请求。所述获取模块42具体用于：在所述视频数据连接请求成功时，根据所述视频数据连接请求获得的视频图像信息，生成所述接收方的第一3D模型；将所述第一3D模型作为所述第一目标3D模型输出。In some embodiments, the network connection request includes a video data connection request. The obtaining module 42 is specifically used for: when the video data connection request is successful, generate the first 3D model of the receiver according to the video image information obtained by the video data connection request; output as the first target 3D model.
在一些实施例中，所述网络连接请求包括图片数据连接请求，所述获取模块具体用于：在所述图片数据连接请求成功时，根据所述图片数据连接请求获得3D模型的图片信息；将所述3D模型的图片信息作为所述接收方的第一目标3D模型输出。In some embodiments, the network connection request includes a picture data connection request, and the obtaining module is specifically configured to: when the picture data connection request succeeds, obtain the picture information of the 3D model according to the picture data connection request; The picture information of the 3D model is output as the first target 3D model of the receiver.
在一些实施例中，所述获取模块具体用于：在所述网络连接请求成功时，根据所述网络连接请求获得的图像信息，获取所述第二接收方的第二背景照片；根据所述获取的第二背景照片，实时生成所述发送方的第二目标3D模型In some embodiments, the obtaining module is specifically configured to: when the network connection request is successful, obtain the second background photo of the second receiver according to the image information obtained in the network connection request; according to the The obtained second background photo is used to generate the second target 3D model of the sender in real time
在一些实施例中，如图4所示，所述装置还包括：第一选择模块44。所述第一选择模块44用于在所述网络连接请求未成功时，从预设模型库中选择一个所述接收方的第二3D模型并将所述第二3D模型作为所述目标3D模型输出。In some embodiments, as shown in FIG. 4 , the device further includes: a first selection module 44 . The first selection module 44 is configured to select a second 3D model of the recipient from a preset model library and use the second 3D model as the target 3D model when the network connection request is unsuccessful output.
在另一些实施例中，所述装置还包括：第二选择模块45，用于获取所述接收方的第二背景照片；根据所述第二背景照片，在预设模型库中获取对应的所述发送方的第二目标3D模型。In some other embodiments, the device further includes: a second selection module 45, configured to obtain a second background photo of the receiver; according to the second background photo, obtain the corresponding The 3D model of the second target of the sender.
具体的，预设模型库可以包括若干个接收方的第二3D模型，若干个接收方的第二3D模型互不相同。当然，该预设模型还可以是发送方的3D模型库。Specifically, the preset model library may include several second 3D models of recipients, and the second 3D models of several recipients are different from each other. Of course, the preset model may also be the sender's 3D model library.
在一些实施例中，如图5所示，所述获取模块42包括：模型生成单元421、指令接收单元422、姿态调整单元423以及输出单元424。In some embodiments, as shown in FIG. 5 , the acquiring module 42 includes: a model generating unit 421 , an instruction receiving unit 422 , an attitude adjusting unit 423 and an output unit 424 .
所述模型生成单元421用于基于所述图像信息,生成初始3D模型。所述指令接收单元422用于接收姿态调整指令。所述姿态调整单元423用于根据所述姿态调整指令，调整所述初始3D模型的姿态。所述输出单元424根据调整后的初始3D模型的姿态，输出所述接收方的第一目标3D模型。The model generating unit 421 is configured to generate an initial 3D model based on the image information. The instruction receiving unit 422 is used for receiving an attitude adjustment instruction. The posture adjustment unit 423 is configured to adjust the posture of the initial 3D model according to the posture adjustment instruction. The output unit 424 outputs the recipient's first target 3D model according to the adjusted pose of the initial 3D model.
在一些实施例中，所述姿态调整单元423具体用于：根据所述角度旋转指令，调整所述接收方的初始3D模型的摆放角度和/或根据所述动作调整指令，调整所述接收方的初始3D模型的动作姿势。In some embodiments, the posture adjustment unit 423 is specifically configured to: adjust the placement angle of the recipient's initial 3D model according to the angle rotation instruction and/or adjust the receiver's initial 3D model according to the action adjustment instruction. The action pose of Fang's initial 3D model.
由于接收方使用的是3D模型，相对于平面照片，可以方便对3D模型进行例如，角度旋转、关节拖动等动作的改变，以使接收方的3D模型经过调整后的姿态与背景照片中的人物或者实物姿态相对应，将该经过调整的3D模型添加至背景照片中，生成的合影照片更自然，无抠图痕迹，这种方法有效的解决了异地合照的问题，并且能够生成更多的美照。Since the recipient is using a 3D model, compared to the plane photo, it is convenient to change the 3D model such as angle rotation, joint dragging, etc., so that the adjusted posture of the recipient's 3D model is consistent with that in the background photo. Corresponding to the posture of the person or the real object, the adjusted 3D model is added to the background photo, and the generated group photo is more natural without traces of matting. This method effectively solves the problem of taking photos in different places and can generate more Beautiful photo.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现合影照片生成装置,当然也可以通过硬件实现。并且，由于合影照片生成装置的构思与上述各个实施例所述的合影照片生成方法的构思一样，在内容不互相冲突下，合影照片生成装置的实施例可以引用上述各个实施例的内容，在此不赘述。Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can realize the group photo generation device by means of software plus a general hardware platform, and of course it can also be realized by hardware. Moreover, since the idea of the group photo generation device is the same as that of the group photo generation method described in the above-mentioned embodiments, the embodiments of the group photo generation device can refer to the contents of the above-mentioned embodiments as long as the contents do not conflict with each other. I won't go into details.
以上所描述的装置或设备实施例仅仅是示意性的，其中所述作为分离部件说明的单元模块可以是或者也可以不是物理上分开的，作为模块单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络模块单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。The device or device embodiments described above are only illustrative, and the unit modules described as separate components may or may not be physically separated, and the components shown as modular units may or may not be physical units , which can be located in one place, or can be distributed to multiple network module units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
本发明实施例提供的合影照片生成装置，通过生成3D模型的方式来合成最终的合影照片，由于接收方使用的是3D模型，相对于平面照片，可以方便对3D模型进行例如，角度旋转、关节拖动等动作的改变，以使接收方的3D模型经过调整后的姿态与背景照片中的人物或者实物姿态相对应，将该经过调整的3D模型添加至背景照片中，生成的合影照片更自然，无抠图痕迹，这种方法有效的解决了异地合照的问题，并且能够生成更多的美照。The group photo generation device provided by the embodiment of the present invention synthesizes the final group photo by generating a 3D model. Since the receiver uses a 3D model, compared with a plane photo, the 3D model can be conveniently, for example, rotated at an angle, jointed, etc. Changes such as dragging, so that the adjusted posture of the recipient's 3D model corresponds to the posture of the person or object in the background photo, and the adjusted 3D model is added to the background photo to generate a more natural group photo , no matting traces, this method effectively solves the problem of taking photos together in different places, and can generate more beautiful photos.
作为本发明实施例的另一方面，本发明实施例提供一种移动终端。如图6所示，该移动终端600包括：一个或多个处理器601以及存储器602。其中，图6中以一个处理器601为例。As another aspect of the embodiments of the present invention, the embodiments of the present invention provide a mobile terminal. As shown in FIG. 6 , the mobile terminal 600 includes: one or more processors 601 and a memory 602 . Wherein, one processor 601 is taken as an example in FIG. 6 .
处理器601和存储器602可以通过总线或者其他方式连接，图6中以通过总线连接为例。The processor 601 and the memory 602 may be connected through a bus or in other ways, and connection through a bus is taken as an example in FIG. 6 .
存储器602作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本发明实施例中的合影照片生成方法对应的程序指令/模块(例如，图4和图5所述的各个模块和单元)。处理器601通过运行存储在存储器602中的非易失性软件程序、指令以及模块，从而执行合影照片生成装置,的各种功能应用以及数据处理，即实现上述方法实施例合影照片生成方法以及上述装置实施例的各个模块的功能。The memory 602, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the program corresponding to the group photo generation method in the embodiment of the present invention Instructions/modules (eg, the various modules and units described in Figures 4 and 5). The processor 601 runs the non-volatile software programs, instructions and modules stored in the memory 602, thereby executing various functional applications and data processing of the group photo generation device, that is, realizing the group photo generation method and the above-mentioned method embodiment. The function of each module of the device embodiment.
存储器602可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器602可选包括相对于处理器601远程设置的存储器，这些远程存储器可以通过网络连接至处理器601。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。The memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 602 may optionally include memory that is remotely located relative to the processor 601, and these remote memories may be connected to the processor 601 through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
所述程序指令/模块存储在所述存储器602中，当被所述一个或者多个处理器601执行时，执行上述任意方法实施例中的合影照片生成方法，例如，执行以上描述的图2至图3所示的各个步骤；也可实现附图图4和图5所述的各个模块和单元的功能。The program instructions/modules are stored in the memory 602, and when executed by the one or more processors 601, execute the group photo generation method in any of the above method embodiments, for example, execute the above-described FIGS. Each step shown in Fig. 3; the functions of each module and unit described in Fig. 4 and Fig. 5 of the accompanying drawings can also be realized.
本发明实施例的移动终端600以多种形式存在，在执行以上描述的图2和图3所示的各个步骤；也可实现图4和图5所述的各个模块和单元的功能时，上述移动终端600包括但不限于：The mobile terminal 600 of the embodiment of the present invention exists in various forms. When executing the steps shown in FIG. 2 and FIG. 3 described above; when the functions of the modules and units described in FIG. 4 and FIG. Mobile terminal 600 includes but not limited to:
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括:上述应用环境中的智能移动终端、多媒体手机、功能性手机，以及低端手机等。(1) Mobile communication equipment: This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication. Such terminals include: intelligent mobile terminals, multimedia mobile phones, functional mobile phones, and low-end mobile phones in the above-mentioned application environments.
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括：PDA、M I D和UMPC设备等，例如i Pad。(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access. Such terminals include: PDA, MID and UMPC equipment, such as iPad.
(3)其他安装有图像处理软件功能和具有上网功能的移动终端。(3) Other mobile terminals equipped with image processing software functions and Internet access functions.
本发明实施例还提供了一种非易失性计算机存储介质，所述计算机存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行，例如图6中的一个处理器601，可使得上述一个或多个处理器可执行上述任意方法实施例中的合影照片生成方法，例如，执行上述任意方法实施例中的合影照片生成方法，例如，执行以上描述的图2和图3所示的各个步骤；也可实现图4和图5所述的各个模块和单元的功能。An embodiment of the present invention also provides a non-volatile computer storage medium, the computer storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, such as a processing in FIG. 6 The device 601 can make the above-mentioned one or more processors execute the method for generating a group photo in any of the above method embodiments, for example, execute the method for generating a group photo in any of the above method embodiments, for example, execute the above-described FIG. 2 and Each step shown in FIG. 3; the functions of each module and unit described in FIG. 4 and FIG. 5 can also be realized.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用直至得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solutions or the part that contributes to related technologies can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, disk , CD, etc., including several instructions until a computer device (which may be a personal computer, server, or network device, etc.) executes the methods described in each embodiment or some parts of the embodiments.
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；在本发明的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明的不同方面的许多其它变化，为了简明，它们没有在细节中提供；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; under the idea of the present invention, the above embodiments or technical features in different embodiments can also be combined, The steps may be performed in any order, and there are many other variations of the different aspects of the invention as described above, which have not been presented in detail for the sake of brevity; although the invention has been described in detail with reference to the preceding examples, those of ordinary skill in the art The skilled person should understand that: it is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the implementation of the present application. The scope of technical solutions.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711213844 | 2017-11-28 | ||
| CN2017112138444 | 2017-11-28 |
| Publication Number | Publication Date |
|---|---|
| CN108053494Atrue CN108053494A (en) | 2018-05-18 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711319430.XAPendingCN108053494A (en) | 2017-11-28 | 2017-12-12 | Group photo generation method and device and mobile terminal |
| Country | Link |
|---|---|
| CN (1) | CN108053494A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766506A (en)* | 2018-11-29 | 2019-05-17 | 北京达佳互联信息技术有限公司 | Image processing method, device, terminal, server and storage medium |
| CN110335207A (en)* | 2019-06-04 | 2019-10-15 | 苏州浩哥文化传播有限公司 | An intelligent image optimization method and system based on group image selection |
| CN110958395A (en)* | 2019-12-18 | 2020-04-03 | 北京软通智慧城市科技有限公司 | VR panorama synthesis method and device |
| CN112492231A (en)* | 2020-11-02 | 2021-03-12 | 重庆创通联智物联网有限公司 | Remote interaction method, device, electronic equipment and computer readable storage medium |
| WO2021109764A1 (en)* | 2019-12-05 | 2021-06-10 | 中兴通讯股份有限公司 | Image or video generation method and apparatus, computing device and computer-readable medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761758A (en)* | 2013-12-27 | 2014-04-30 | 一派视觉（北京）数字科技有限公司 | Travel virtual character photographing method and system |
| CN104580930A (en)* | 2013-10-28 | 2015-04-29 | 腾讯科技（深圳）有限公司 | Group photo taking method and system |
| CN106331529A (en)* | 2016-10-27 | 2017-01-11 | 广东小天才科技有限公司 | Image shooting method and device |
| CN106375193A (en)* | 2016-09-09 | 2017-02-01 | 四川长虹电器股份有限公司 | Remote group photographing method |
| KR20170027165A (en)* | 2015-09-01 | 2017-03-09 | 엘지전자 주식회사 | Mobile terminal and method for controlling the same |
| CN106558087A (en)* | 2015-09-30 | 2017-04-05 | 捷荣科技集团有限公司 | Virtual tourism method and system based on human body model |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104580930A (en)* | 2013-10-28 | 2015-04-29 | 腾讯科技（深圳）有限公司 | Group photo taking method and system |
| CN103761758A (en)* | 2013-12-27 | 2014-04-30 | 一派视觉（北京）数字科技有限公司 | Travel virtual character photographing method and system |
| KR20170027165A (en)* | 2015-09-01 | 2017-03-09 | 엘지전자 주식회사 | Mobile terminal and method for controlling the same |
| CN106558087A (en)* | 2015-09-30 | 2017-04-05 | 捷荣科技集团有限公司 | Virtual tourism method and system based on human body model |
| CN106375193A (en)* | 2016-09-09 | 2017-02-01 | 四川长虹电器股份有限公司 | Remote group photographing method |
| CN106331529A (en)* | 2016-10-27 | 2017-01-11 | 广东小天才科技有限公司 | Image shooting method and device |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766506A (en)* | 2018-11-29 | 2019-05-17 | 北京达佳互联信息技术有限公司 | Image processing method, device, terminal, server and storage medium |
| CN109766506B (en)* | 2018-11-29 | 2021-04-16 | 北京达佳互联信息技术有限公司 | Picture processing method, device, terminal, server and storage medium |
| CN110335207A (en)* | 2019-06-04 | 2019-10-15 | 苏州浩哥文化传播有限公司 | An intelligent image optimization method and system based on group image selection |
| WO2021109764A1 (en)* | 2019-12-05 | 2021-06-10 | 中兴通讯股份有限公司 | Image or video generation method and apparatus, computing device and computer-readable medium |
| CN110958395A (en)* | 2019-12-18 | 2020-04-03 | 北京软通智慧城市科技有限公司 | VR panorama synthesis method and device |
| CN112492231A (en)* | 2020-11-02 | 2021-03-12 | 重庆创通联智物联网有限公司 | Remote interaction method, device, electronic equipment and computer readable storage medium |
| Publication | Publication Date | Title |
|---|---|---|
| CN111050072B (en) | Method, equipment and storage medium for remote co-shooting | |
| TWI650675B (en) | Method and system for group video session, terminal, virtual reality device and network device | |
| CN108053494A (en) | Group photo generation method and device and mobile terminal | |
| US20200329214A1 (en) | Method and system for providing mixed reality service | |
| US20180130259A1 (en) | System, Device or Method for Collaborative Augmented Reality | |
| JP2023538958A (en) | Photography methods, equipment, electronic equipment and computer-readable storage media | |
| JP2014112302A (en) | Prescribed area management system, communication method, and program | |
| KR20190013308A (en) | Mobile terminal and method for controlling the same | |
| CN103812907B (en) | A kind of methods, devices and systems for determining terminal to be shared | |
| WO2022048651A1 (en) | Cooperative photographing method and apparatus, electronic device, and computer-readable storage medium | |
| CN108600632A (en) | It takes pictures reminding method, intelligent glasses and computer readable storage medium | |
| CN107451953A (en) | Group photo generation method and device and electronic equipment | |
| US12389120B2 (en) | Communication terminal, image communication system, and method of displaying image | |
| JP7604829B2 (en) | Image communication system, communication management device, communication management method and program | |
| JP2024127983A (en) | Information processing system, communication system, image sharing method, and program | |
| CN114979564A (en) | Video shooting method, electronic equipment, device, system and medium | |
| CN110433491A (en) | Movement sync response method, system, device and the storage medium of virtual spectators | |
| CN107197147A (en) | The method of controlling operation thereof and device of a kind of panorama camera | |
| CN110413109A (en) | Method, device, system, electronic device and storage medium for generating virtual content | |
| CN118355407A (en) | 3D Models for Augmented Reality (AR) | |
| KR20240010010A (en) | Hardware encoder for stereo stitching | |
| JP5972302B2 (en) | Operator terminal, portable terminal, instruction transmission method, program for operator terminal | |
| CN117478819A (en) | Physical display methods, devices and systems for remote conferences | |
| JP2023121637A (en) | Information processing system, communication system, image transmitting method, and program | |
| CN113542609A (en) | Graduation memory system based on augmented reality technology and panoramic video technology and use method |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20180518 |