- Notifications
You must be signed in to change notification settings - Fork4
License
NotificationsYou must be signed in to change notification settings
wildrgbd/wildrgbd
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Hongchi Xia1*, Yang Fu2*, Sifei Liu3, Xiaolong Wang2
*Equal contribution
1Shanghai Jiao Tong University,2University of California San Diego,3NVIDIA
*Equal contribution
1Shanghai Jiao Tong University,2University of California San Diego,3NVIDIA
To download full WildRGB-D Dataset, it totally requires approximately 3.37T disk space to store zip packages, and approximately 4T to store all data.
To download all categories, executepython download.py --cat all.
To download specific one category, executepython download.py --cat <category_name>.
You could check all category names in the download scripts.
WildRGB-D ├── <category_name> │ ├── scenes │ │ ├── scenes_<scene_id> │ │ │ ├── rgb │ │ │ │ ├── <frame_id>.png │ │ │ │ | │ │ │ ├── depth │ │ │ │ ├── <frame_id>.png │ │ │ │ | │ │ │ ├── masks │ │ │ │ ├── <frame_id>.png │ │ │ │ | │ │ │ ├── metadata │ │ │ ├── cam_poses.txt │├── types.json │├── nvs_list.json │├── camera_eval_list.json<category_name>/scenes/scenes_<scene_id>/depth/: We store depths in the depth scale of 1000. That is, when we load depth image and divide by 1000, we could get depth in meters.<category_name>/scenes/scenes_<scene_id>/metadata: It stores the camera intrinsics including image width, height and K.<category_name>/scenes/scenes_<scene_id>/cam_poses.txt: It stores the camera extrinsics. For every line, we list the <frame_id> first, then following the flatten 4x4 extrinsic matrix. Our camera extrinsics follows OpenCV convention, and it's camera to world matrix.<category_name>/types.json: It stores the video type of every scene in<category_name>/scenes/. It includes single object video marked in "single", multi-object video marked in "multi" and hand-object video marked in "hand".<category_name>/nvs_list.json: It stores the training and validation split we use in our Novel View Synthesis Task. For Single-Scene NVS, we only test on val split. For Cross-Scene NVS, we pre-train on train split and test on val split.<category_name>/camera_eval_list.json: It stores the training and validation split we use in our Camera Pose Evaluation Task.
Our WildRGB-D Dataset provides point cloud annotations. Please refer towildrgbd_generate_point_cloud.py.
If you have any problems when downloading and using WildRGB-D Dataset, please contactHongchi Xia by email.