CN109767389B - Self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local combined prior - Google Patents
Self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local combined priorDownload PDFInfo
- Publication number
- CN109767389B CN109767389BCN201910035555.2ACN201910035555ACN109767389BCN 109767389 BCN109767389 BCN 109767389BCN 201910035555 ACN201910035555 ACN 201910035555ACN 109767389 BCN109767389 BCN 109767389B
- Authority
- CN
- China
- Prior art keywords
- image
- resolution
- reconstruction
- norm
- local
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription82
- 230000003044adaptive effectEffects0.000claimsabstractdescription16
- 239000011159matrix materialSubstances0.000claimsdescription6
- 230000000694effectsEffects0.000claimsdescription2
- 230000001629suppressionEffects0.000claimsdescription2
- 230000001568sexual effectEffects0.000claims1
- 238000002474experimental methodMethods0.000description7
- 238000012360testing methodMethods0.000description5
- 238000012545processingMethods0.000description4
- 230000015556catabolic processEffects0.000description3
- 238000006731degradation reactionMethods0.000description3
- 238000005516engineering processMethods0.000description3
- 238000011156evaluationMethods0.000description3
- QQEHDZXXCDSAFE-JBSAMAPISA-N[(3s,8r,9s,10r,13s,14s,17r)-17-acetyl-6-chloro-3-hydroxy-10,13-dimethyl-1,2,3,8,9,11,12,14,15,16-decahydrocyclopenta[a]phenanthren-17-yl] acetateChemical compoundC1=C(Cl)C2=C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@@](C(C)=O)(OC(=O)C)[C@@]1(C)CC2QQEHDZXXCDSAFE-JBSAMAPISA-N0.000description2
- 238000010586diagramMethods0.000description2
- 238000004891communicationMethods0.000description1
- 238000012733comparative methodMethods0.000description1
- 238000003909pattern recognitionMethods0.000description1
- 230000000007visual effectEffects0.000description1
Images
Classifications
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Image Processing (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明涉及图像分辨率提升技术，具体涉及一种基于局部和非局部联合先验的自适应加权双范数遥感图像盲超分辨重建方法，属于图像处理领域。The invention relates to an image resolution improvement technology, in particular to an adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local joint priors, belonging to the field of image processing.
背景技术Background technique
高分辨率的遥感图像在军事、农业、民生等领域得到广泛的应用。然而，遥感图像的获取容易受到振动和运动的影响，造成模糊退化，因此遥感图像的质量可能不尽如人意。通常情况下，图像降质包括模糊和下采样。因此，在实际应用中，通过图像处理技术来针对性地提升已获取的遥感图像的质量，是很有必要的。为了解决这些问题，人们对图像去模糊和分辨率提升进行了广泛的研究。本文对这一问题进行了研究，称为盲超分辨率重建。单幅图像超分辨率重建技术是提升图像分辨率的方法之一，其具有易于实现、成本低、适用性强等特点，它由观测的单幅低分辨率图像估计对应的高分辨率图像。由于同一低分辨率图像可能对应多个不同的高分辨率图像，单幅图像超分辨率重建问题具有严重的病态性。因此需要通过图像先验约束以得到一个稳定、可靠的高分辨率估计。目前的单幅图像超分辨率重建方法大致可以分为三类：基于插值的超分辨率方法、基于重建的超分辨率方法和基于学习的超分辨率方法。这三类方法具有不同的特点，如基于插值的方法通常仅根据插值核来获取插值图像，较少考虑模糊以及噪声的影响，应用范围相对有限。基于重建的超分辨率方法充分挖掘降质图像自身的信息，通常能较好地抑制人工痕迹。基于学习的方法往往具有较快的执行速度，并且能很好地恢复图像细节。此外，在未知的模糊核下进行超分辨率重建是图像恢复面临的一个更大的挑战，即为盲超分辨率重建。盲超分辨率重建通常分为模糊核估计和非盲超分辨率重建两个子过程。High-resolution remote sensing images are widely used in military, agriculture, people's livelihood and other fields. However, the acquisition of remote sensing images is easily affected by vibration and motion, causing blur degradation, so the quality of remote sensing images may not be satisfactory. Typically, image degradation includes blurring and downsampling. Therefore, in practical applications, it is necessary to improve the quality of acquired remote sensing images through image processing technology. To address these issues, image deblurring and resolution enhancement have been extensively studied. This paper investigates this problem, called blind super-resolution reconstruction. Single image super-resolution reconstruction technology is one of the methods to improve image resolution. It has the characteristics of easy implementation, low cost, and strong applicability. It estimates the corresponding high-resolution image from a single observed low-resolution image. Since the same low-resolution image may correspond to multiple different high-resolution images, the single-image super-resolution reconstruction problem is seriously ill-conditioned. Therefore, image prior constraints are required to obtain a stable and reliable high-resolution estimate. Current single-image super-resolution reconstruction methods can be broadly classified into three categories: interpolation-based super-resolution methods, reconstruction-based super-resolution methods, and learning-based super-resolution methods. These three types of methods have different characteristics. For example, interpolation-based methods usually only obtain interpolation images based on the interpolation kernel, less consideration is given to the influence of blur and noise, and the application range is relatively limited. The reconstruction-based super-resolution method fully mines the information of the degraded image itself, and can usually suppress artifacts better. Learning-based methods tend to have fast execution speeds and recover image details well. In addition, performing super-resolution reconstruction under an unknown blur kernel is a greater challenge for image restoration, namely blind super-resolution reconstruction. Blind super-resolution reconstruction is usually divided into two sub-processes: blur kernel estimation and non-blind super-resolution reconstruction.
发明内容Contents of the invention
本发明的目的是有机地将模糊核估计和非盲超分辨率两个子过程结合，进而构建一种高效率、高性能的遥感图像超分辨率盲重建方法。The purpose of the present invention is to organically combine the two sub-processes of fuzzy kernel estimation and non-blind super-resolution, and then construct a high-efficiency, high-performance remote sensing image super-resolution blind reconstruction method.
本发明提出的基于局部和非局部联合先验的自适应加权双范数遥感图像盲超分辨重建方法，主要包括以下操作步骤：The self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local joint priors proposed by the present invention mainly includes the following steps:
(1)在模糊核估计子过程，使用自适应加权双范数先验，以得到估计的模糊核和初始高分辨率图像；(1) In the blur kernel estimation sub-process, use the adaptive weighted double norm prior to obtain the estimated blur kernel and the initial high-resolution image;
(2)将估计的模糊核和初始高分辨率图像作为非盲重建子过程的输入；(2) The estimated blur kernel and the initial high-resolution image are used as input to the non-blind reconstruction subprocess;
(3)在非盲重建子过程，估计的模糊核和初始高分辨率图像作为已知条件，利用局部和非局部的联合先验及最大后验概率重建模型估计出高分辨率图像。(3) In the non-blind reconstruction sub-process, the estimated blur kernel and the initial high-resolution image are used as known conditions, and the high-resolution image is estimated by using the local and non-local joint prior and maximum posterior probability reconstruction models.
(4)以步骤(3)的重建结果作为新的输入高分辨率图像，重复执行步骤(3)和步骤(4)，直到达到最大重建建次数，最后输出即为最终重建结果。(4) Take the reconstruction result of step (3) as a new input high-resolution image, repeat steps (3) and (4) until the maximum number of reconstructions is reached, and the final output is the final reconstruction result.
附图说明Description of drawings
图1是本发明基于局部和非局部联合先验的自适应加权双范数遥感图像盲超分辨重建方法的原理框图Fig. 1 is the functional block diagram of the blind super-resolution reconstruction method of adaptive weighted double-norm remote sensing image based on local and non-local joint prior of the present invention
图2是初始高分辨率图像和双三次重建图像对比图：其中，(a)(c)为模糊核子过程得到二倍重建初始高分辨率图像，(b)(d)为使用双三次二倍重建的结果Figure 2 is a comparison of the initial high-resolution image and the bicubic reconstruction image: (a) (c) is the initial high-resolution image obtained by the fuzzy kernel process twice, and (b) (d) is the use of bicubic double The result of reconstruction
图3是本发明与其他方法模糊核估计结果对比图：其中，(a)(e)(i)为真实模糊核图像，(b)(f)(j)为本发明估计的模糊核，(c)(g)(k)为去模糊对比方法1估计的模糊核，(d)(h)(l)为去模糊对比方法2估计的模糊核Fig. 3 is the comparison figure of the present invention and other method fuzzy kernel estimation results: wherein, (a) (e) (i) is the real fuzzy kernel image, (b) (f) (j) is the fuzzy kernel estimated by the present invention, ( c)(g)(k) is the blur kernel estimated by
图4是本发明与六种方法对测试图像“mobilehomepark”二倍重建结果的对比图：其中，(a)为输入低分辨率图像，(i)为原始高分辨率图像，(b)(c)(d)(e)(f)(g)(h)分别为对比方法1、对比方法2、对比方法3、对比方法4、对比方法5、Bicubic及本发明的重建结果Fig. 4 is a comparison diagram of the double reconstruction results of the test image "mobilehomepark" by the present invention and six methods: (a) is the input low-resolution image, (i) is the original high-resolution image, (b) (c )(d)(e)(f)(g)(h) are respectively the reconstruction results of
具体实施方式Detailed ways
下面结合附图对本发明作进一步说明：The present invention will be further described below in conjunction with accompanying drawing:
图1中，基于局部和非局部联合先验的自适应加权双范数遥感图像盲超分辨重建方法，具体可以分为以下几个步骤：In Figure 1, the adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local joint priors can be divided into the following steps:
(1)在模糊核估计子过程，使用自适应加权双范数先验，以得到估计的模糊核和初始高分辨率图像；(1) In the blur kernel estimation sub-process, use the adaptive weighted double norm prior to obtain the estimated blur kernel and the initial high-resolution image;
(2)将估计的模糊核和初始高分辨率图像作为非盲重建子过程的输入；(2) The estimated blur kernel and the initial high-resolution image are used as input to the non-blind reconstruction subprocess;
(3)在非盲重建子过程，估计的模糊核和初始高分辨率图像作为已知条件，利用局部和非局部的联合先验及最大后验概率重建模型估计出高分辨率图像。(3) In the non-blind reconstruction sub-process, the estimated blur kernel and the initial high-resolution image are used as known conditions, and the high-resolution image is estimated by using the local and non-local joint prior and maximum posterior probability reconstruction models.
(4)以步骤(3)的重建结果作为新的输入高分辨率图像，重复执行步骤(3)和步骤(4)，直到达到最大重建建次数，最后输出即为最终重建结果。(4) Take the reconstruction result of step (3) as a new input high-resolution image, repeat steps (3) and (4) until the maximum number of reconstructions is reached, and the final output is the final reconstruction result.
具体地，所述步骤(1)中，我们首先输入低分辨率模糊图像，构建基于最大后验概率的重建框架，该框架中采用自适应加权双范数先验和卷积一致性先验作为约束条件，其中自适应加权双范数先验分别约束估计的模糊核和估计的高分辨率图像，卷积一致性先验约束估计的高分辨率图像。如公式(1)所示：Specifically, in the step (1), we first input a low-resolution blurred image, and construct a reconstruction framework based on maximum a posteriori probability. In this framework, adaptive weighted bi-norm priors and convolutional consistency priors are used as constraints, where the adaptive weighted bi-norm prior constrains the estimated blur kernel and the estimated high-resolution image, respectively, and the convolutional consistency prior constrains the estimated high-resolution image. As shown in formula (1):
λ表示第一项去模糊图像卷积输出的参数；H是模糊核k的矩阵表示；D是降低原始高分辨率图像分辨率的下采样矩阵；x是原始高分辨率图像，y是观察到的低分辨率模糊图像；αx，βx，αk，βk是正则化参数；η是卷积一致性约束参数；
它代表了一个以第i个像素为中心的5*5图像块的局部非光滑性。Xi是该图像块的中心像素，Ωi是该图像块中所有像素索引集，Xij是Xi在j位置的近邻像素。It represents the local non-smoothness of a 5×5 image patch centered at the i-th pixel. Xi is the central pixel of the image block, Ωi is the index set of all pixels in the image block, and Xij is the neighbor pixel of Xi at position j.
通过步骤(1)，可得到估计的模糊核k和初始高分辨率图像x。Through step (1), the estimated blur kernel k and the initial high-resolution image x can be obtained.
所述步骤(2)中，我们通过超分辨率非盲重建子过程重建高分辨率图像。其中在步骤(1)中得到的估计的模糊核k和初始高分辨率图像x作为已知的输入项，从而将前后两个子过程结合起来，如图1。In the step (2), we reconstruct a high-resolution image through a super-resolution non-blind reconstruction sub-process. The estimated blur kernel k and the initial high-resolution image x obtained in step (1) are used as known input items, so that the two sub-processes are combined, as shown in Figure 1.
所述步骤(3)中，我们构建基于最大后验概率的重建框架，利用联合局部和非局部的先验作为图像先验，见公式(3):In the step (3), we construct a reconstruction framework based on maximum a posteriori probability, and utilize joint local and non-local priors as image priors, see formula (3):
其中JAHNLTV是非局部的图像先验，JAGD是局部的图像先验，ζ和θ是平衡上述两个先验的正则化参数。在此步骤中，模糊核已知且初始高分辨率图像作为迭代起点，从而重建出高分辨率图像。where JAHNLTV is a non-local image prior, JAGD is a local image prior, and ζ and θ are regularization parameters to balance the above two priors. In this step, the blur kernel is known and the initial high-resolution image is used as the iterative starting point to reconstruct a high-resolution image.
所述步骤(4)中，我们将步骤(3)的结果作为新的初始高分辨率图像，重复执行步骤(3)和步骤(4)。直到达到设定的最大重建次数，重建结果即为最终的输出。In the step (4), we use the result of the step (3) as a new initial high-resolution image, and repeatedly execute the steps (3) and (4). Until the set maximum number of reconstructions is reached, the reconstruction result is the final output.
为了更好地说明本发明的有效性，分别进行了初始高分辨率图像比较实验，模糊核估计比较实验，和在常用测试图像“mobilehomepark”上进行了最终高分辨率图像的重建比较实验。In order to better illustrate the effectiveness of the present invention, the initial high-resolution image comparison experiment, the blur kernel estimation comparison experiment, and the final high-resolution image reconstruction comparison experiment on the commonly used test image "mobilehomepark" were carried out.
初始高分辨率图像比较实验如图2所示。图2(a)和图2(c)是由本发明模糊核估计子过程2倍重建得到的初始高分辨率图像，图2(b)和图2(d)是对原始观察的低分辨率采用双三次2倍重建的高分辨率图像。The initial high-resolution image comparison experiment is shown in Fig. 2. Fig. 2 (a) and Fig. 2 (c) are the initial high-resolution images obtained by 2 times reconstruction of the fuzzy kernel estimation sub-process of the present invention, and Fig. 2 (b) and Fig. 2 (d) are low-resolution images of the original observation High resolution image of bicubic 2x reconstruction.
模糊核估计比较实验如图3所示。(a)(e)(i)为真实模糊核图像，(b)(f)(j)为本发明估计的模糊核，(c)(g)(k)为去模糊对比方法1估计的模糊核，(d)(h)(l)为去模糊对比方法2估计的模糊核。两种对比的算法为：The fuzzy kernel estimation comparison experiment is shown in Fig. 3. (a)(e)(i) is the real blur kernel image, (b)(f)(j) is the blur kernel estimated by the present invention, (c)(g)(k) is the blur estimated by
去模糊对比方法1：Xu等人提出的方法，参考文献“Xu L,Zheng S,Jia J.“Unnatural l0 sparse representation for natural image deblurring,”Proceedingsof the IEEE conference on computer vision and pattern recognition.2013:1107-1114.”。Deblurring comparison method 1: The method proposed by Xu et al., reference "Xu L, Zheng S, Jia J. "Unnatural l0 sparse representation for natural image deblurring," Proceedings of the IEEE conference on computer vision and pattern recognition.2013:1107 -1114.".
去模糊对比方法2：Shao等人提出的方法，参考文献“Shao W Z,Li H B,Elad M,“Bi-l0-l2-norm regularization for blind motion deblurring,”Journal ofVisualCommunication and Image Representation,2015,33:42-59.”。Deblurring comparison method 2: The method proposed by Shao et al., reference "Shao W Z, Li H B, Elad M, "Bi-l0-l2-norm regularization for blind motion deblurring," Journal of Visual Communication and Image Representation, 2015, 33: 42-59.".
最终高分辨率图像的重建比较实验如图4所示。(a)为输入低分辨率图像，(i)为原始高分辨率图像，(b)(c)(d)(e)(f)(g)(h)分别为对比方法1、对比方法2、对比方法3、对比方法4、对比方法5、Bicubic及本发明的重建结果。The reconstruction comparison experiment of the final high-resolution image is shown in Fig. 4. (a) is the input low-resolution image, (i) is the original high-resolution image, (b) (c) (d) (e) (f) (g) (h) are
对比方法1：Shao等人提出的方法，参考文献“Shao W Z,Elad M,“Simple,accurate,and robust nonparametric blind super-resolution,”InternationalConference on Image and Graphics.Springer,Cham,2015:333-348.”。Comparison method 1: The method proposed by Shao et al., reference "Shao W Z, Elad M, "Simple, accurate, and robust nonparametric blind super-resolution," International Conference on Image and Graphics. Springer, Cham, 2015:333-348. ".
对比方法2：模糊核估计子过程采用去模糊对比方法2，非盲重建子过程：Buades等人提出的方法，参考文献“Buades A,Coll B,Morel J M,“Image enhancement by non-local reverse heat equation,”Preprint CMLA,2006,22:2006.”。Comparison method 2: The blur kernel estimation sub-process adopts the deblurring comparison method 2, and the non-blind reconstruction sub-process: the method proposed by Buades et al., reference "Buades A, Coll B, Morel J M, "Image enhancement by non-local reverse heat equation, "Preprint CMLA, 2006, 22:2006.".
对比方法3：模糊核估计子过程采用去模糊对比方法2，非盲重建子过程：Ren等人提出的方法，参考文献“Ren C,He X,Nguyen T Q,“Single image super-resolution viaadaptive high-dimensional non-local total variation and adaptive geometricfeature,”IEEE Transactions on Image Processing,2017,26(1):90-106.”。Comparison method 3: Deblurring comparison method 2 is used for the fuzzy kernel estimation sub-process, and the non-blind reconstruction sub-process: the method proposed by Ren et al., reference "Ren C, He X, Nguyen T Q, "Single image super-resolution via adaptive high- dimensional non-local total variation and adaptive geometric feature,"IEEE Transactions on Image Processing,2017,26(1):90-106.".
对比方法4：模糊核估计子过程采用去模糊对比方法1，非盲重建子过程：Dong等人提出的方法，参考文献“Dong W,Zhang L,Shi G,et al,“Nonlocally centralized sparserepresentation for image restoration,”IEEE Transactions on Image Processing,2013,22(4):1620-1630.”。Comparison method 4: The fuzzy kernel estimation sub-process adopts the
对比方法5：模糊核估计子过程采用去模糊对比方法1，非盲重建子过程：Buades等人提出的方法，参考文献“Buades A,Coll B,Morel J M,“Image enhancement by non-local reverse heat equation,”Preprint CMLA,2006,22:2006.”。Comparison method 5:
最终高分辨率图像的重建对比实验的内容如下：The content of the reconstruction comparison experiment of the final high-resolution image is as follows:
分别用Bicubic，方法1，方法2，方法3，方法4，方法5以及本发明对由遥感测试图像库“UCMerced”模拟生成的低分辨率模糊图像进行2倍重建。低分辨率图像的模糊降质由八种模糊核实现。超分辨率重建结果的客观评价参数如表一所示。其中客观评价参数PSNR(Peak Signal to Noise Ratio)、SSIM(Structure Similarity Index)均为值越大，代表图像质量越好。算法测试平台：处理器Inter Core i5CPU(3.3GHz)及内存16G的台式计算机。Bicubic,
表一Table I
从表一所示的客观参数上看，在遥感图像测试库上针对八种不同的模糊核本发明都取得了最高的PSNR、SSIM值，代表着本发明重建结果的质量更好。From the objective parameters shown in Table 1, the present invention has achieved the highest PSNR and SSIM values for eight different fuzzy kernels on the remote sensing image test database, which means that the quality of the reconstruction results of the present invention is better.
综上所述，相比于对比方法，本发明的重建结果在主客观评价上都有一定优势。因此，本发明是一种高性能的单幅图像超分辨率重建方法。To sum up, compared with the comparative method, the reconstruction result of the present invention has certain advantages in subjective and objective evaluation. Therefore, the present invention is a high-performance single image super-resolution reconstruction method.
Claims (1)
Translated fromChinese
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035555.2ACN109767389B (en) | 2019-01-15 | 2019-01-15 | Self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local combined prior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035555.2ACN109767389B (en) | 2019-01-15 | 2019-01-15 | Self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local combined prior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109767389A CN109767389A (en) | 2019-05-17 |
| CN109767389Btrue CN109767389B (en) | 2023-06-20 |
Family
ID=66454040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910035555.2AActiveCN109767389B (en) | 2019-01-15 | 2019-01-15 | Self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local combined prior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767389B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113096013B (en)* | 2021-03-31 | 2021-11-26 | 南京理工大学 | Blind image super-resolution reconstruction method and system based on imaging modeling and knowledge distillation |
| CN113627357B (en)* | 2021-08-13 | 2022-07-08 | 哈尔滨工业大学 | High-spatial-high-spectral-resolution intrinsic decomposition method and system for remote sensing image |
| US20240185386A1 (en)* | 2021-09-30 | 2024-06-06 | Baidu Usa Llc | Robust and efficient blind super-resolution using variational kernel autoencoder |
| CN114202459B (en)* | 2021-10-26 | 2024-03-22 | 北京工业大学 | Blind image super-resolution method based on depth priori |
| CN119831838A (en)* | 2023-10-10 | 2025-04-15 | 四川大学 | Depth image super-resolution method based on non-local and local priori |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005055136A2 (en)* | 2003-11-26 | 2005-06-16 | Board Of Regents, The University Of Texas System | Method and apparatus for phase-sensitive magnetic resonance imaging |
| JP2008154237A (en)* | 1998-04-06 | 2008-07-03 | Seiko Epson Corp | Image data interpolation apparatus, computer for image data interpolation processing, image data interpolation method, and medium on which image data interpolation program is recorded |
| WO2010050914A1 (en)* | 2008-10-31 | 2010-05-06 | Hewlett-Packard Development Company, L.P. | Method and system for enhancing image signals to alter the perception of depth by human viewers |
| CN104217405A (en)* | 2014-09-23 | 2014-12-17 | 闽江学院 | Salt-pepper noise filter method for image fusing local information and global information |
| WO2015084966A2 (en)* | 2013-12-04 | 2015-06-11 | Razzor Technologies Inc. | Adaptive sharpening in image processing and display |
| WO2015180053A1 (en)* | 2014-05-28 | 2015-12-03 | 北京大学深圳研究生院 | Method and apparatus for rapidly reconstructing super-resolution image |
| US9237257B1 (en)* | 2013-06-14 | 2016-01-12 | Xilinx, Inc. | Circuits for and methods of generating a digital image |
| CN107025632A (en)* | 2017-04-13 | 2017-08-08 | 首都师范大学 | A kind of image super-resolution rebuilding method and system |
| CN109064402A (en)* | 2018-07-27 | 2018-12-21 | 四川大学 | Based on the single image super resolution ratio reconstruction method for enhancing non local total variation model priori |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8269727B2 (en)* | 2007-01-03 | 2012-09-18 | Apple Inc. | Irregular input identification |
| US8422788B2 (en)* | 2008-08-26 | 2013-04-16 | Microsoft Corporation | Automatic image straightening |
| US8330827B2 (en)* | 2009-11-19 | 2012-12-11 | Eastman Kodak Company | Increasing image resolution using combined differential image |
| US20110122224A1 (en)* | 2009-11-20 | 2011-05-26 | Wang-He Lou | Adaptive compression of background image (acbi) based on segmentation of three dimentional objects |
| US8594464B2 (en)* | 2011-05-26 | 2013-11-26 | Microsoft Corporation | Adaptive super resolution for video enhancement |
| US9692939B2 (en)* | 2013-05-29 | 2017-06-27 | Yeda Research And Development Co. Ltd. | Device, system, and method of blind deblurring and blind super-resolution utilizing internal patch recurrence |
| JP6236259B2 (en)* | 2013-09-06 | 2017-11-22 | 株式会社東芝 | Image processing apparatus, image processing method, and image processing program |
| CN105205783B (en)* | 2015-09-14 | 2016-11-16 | 河海大学 | A Blind Super-resolution Reconstruction Method for SAR Images Based on Joint Prior Estimation |
| CN105550989B (en)* | 2015-12-09 | 2018-11-30 | 西安电子科技大学 | The image super-resolution method returned based on non local Gaussian process |
| CN105913392A (en)* | 2016-04-08 | 2016-08-31 | 西安电子科技大学昆山创新研究院 | Degraded image overall quality improving method in complex environment |
| CN106251297A (en)* | 2016-07-19 | 2016-12-21 | 四川大学 | A kind of estimation based on multiple image fuzzy core the rebuilding blind super-resolution algorithm of improvement |
| CN107680040A (en)* | 2017-09-26 | 2018-02-09 | 北京空间飞行器总体设计部 | A kind of blind convolution super-resolution reconstruction method of multiframe based on bayesian criterion and device |
- 2019
- 2019-01-15CNCN201910035555.2Apatent/CN109767389B/enactiveActive
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008154237A (en)* | 1998-04-06 | 2008-07-03 | Seiko Epson Corp | Image data interpolation apparatus, computer for image data interpolation processing, image data interpolation method, and medium on which image data interpolation program is recorded |
| WO2005055136A2 (en)* | 2003-11-26 | 2005-06-16 | Board Of Regents, The University Of Texas System | Method and apparatus for phase-sensitive magnetic resonance imaging |
| WO2010050914A1 (en)* | 2008-10-31 | 2010-05-06 | Hewlett-Packard Development Company, L.P. | Method and system for enhancing image signals to alter the perception of depth by human viewers |
| US9237257B1 (en)* | 2013-06-14 | 2016-01-12 | Xilinx, Inc. | Circuits for and methods of generating a digital image |
| WO2015084966A2 (en)* | 2013-12-04 | 2015-06-11 | Razzor Technologies Inc. | Adaptive sharpening in image processing and display |
| WO2015180053A1 (en)* | 2014-05-28 | 2015-12-03 | 北京大学深圳研究生院 | Method and apparatus for rapidly reconstructing super-resolution image |
| CN104217405A (en)* | 2014-09-23 | 2014-12-17 | 闽江学院 | Salt-pepper noise filter method for image fusing local information and global information |
| CN107025632A (en)* | 2017-04-13 | 2017-08-08 | 首都师范大学 | A kind of image super-resolution rebuilding method and system |
| CN109064402A (en)* | 2018-07-27 | 2018-12-21 | 四川大学 | Based on the single image super resolution ratio reconstruction method for enhancing non local total variation model priori |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109767389A (en) | 2019-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767389B (en) | Self-adaptive weighted double-norm remote sensing image blind super-resolution reconstruction method based on local and non-local combined prior | |
| Zhang et al. | High-quality image restoration using low-rank patch regularization and global structure sparsity | |
| Pan et al. | Dual convolutional neural networks for low-level vision | |
| CN109389552B (en) | Image super-resolution algorithm based on context-dependent multitask deep learning | |
| CN101639938B (en) | Image restoration method based on double-edge wave filter and margin deconvolution | |
| Min et al. | Blind deblurring via a novel recursive deep CNN improved by wavelet transform | |
| CN112488920B (en) | A method for image regularization super-resolution reconstruction based on Gaussian-like blur kernel | |
| CN115345791A (en) | An Infrared Image Deblurring Algorithm Based on Residual Network Model of Attention Mechanism | |
| CN117726537B (en) | SAR image denoising network method and system based on adaptive multi-scale feature fusion AMFFD-Net | |
| CN116523790B (en) | SAR image denoising optimization method, system and storage medium | |
| Wang et al. | An improved image blind deblurring based on dark channel prior | |
| Ren et al. | Learning image profile enhancement and denoising statistics priors for single-image super-resolution | |
| Zhao et al. | Deep pyramid generative adversarial network with local and nonlocal similarity features for natural motion image deblurring | |
| GR | Learning-based super-resolution for image upscaling using sparse representation | |
| CN111382845B (en) | Template reconstruction method based on self-attention mechanism | |
| CN107085826B (en) | Image super-resolution reconstruction method based on weighted overlapping non-local regression priors | |
| CN110852947A (en) | A super-resolution method for infrared images based on edge sharpening | |
| Zin et al. | Local image denoising using RAISR | |
| CN102156967A (en) | Multiscale-based local image interpolation method | |
| CN117196956A (en) | Infrared image super-resolution reconstruction method based on dense residual error connection network | |
| CN108062743B (en) | Super-resolution method for noisy image | |
| CN116596757A (en) | Depth image super-resolution method and device based on non-local autoregressive model | |
| Wu et al. | VDIP-TGV: Blind image deconvolution via variational deep image prior empowered by total generalized variation | |
| Nawaz et al. | Image super resolution by sparse linear regression and iterative back projection | |
| Huang et al. | A non-local enhanced network for image restoration |
Legal Events
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |