{"id":15630960,"url":"https://github.com/junyanz/light-field-video","last_synced_at":"2025-07-08T13:13:04.404Z","repository":{"id":72158710,"uuid":"90620310","full_name":"junyanz/light-field-video","owner":"junyanz","description":" Light field video applications (e.g. video refocusing, focus tracking, changing aperture and view) ","archived":false,"fork":false,"pushed_at":"2020-08-05T01:13:29.000Z","size":4429,"stargazers_count":203,"open_issues_count":3,"forks_count":42,"subscribers_count":13,"default_branch":"master","last_synced_at":"2025-04-07T09:44:40.526Z","etag":null,"topics":["caffe","computer-graphics","computer-vision","deep-learning","lightfield"],"latest_commit_sha":null,"homepage":"http://cseweb.ucsd.edu/~viscomp/projects/LF/papers/SIG17/lfv/","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/junyanz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-05-08T11:25:39.000Z","updated_at":"2024-11-04T01:40:36.000Z","dependencies_parsed_at":null,"dependency_job_id":"771a91c5-3a82-4402-80f8-bf42b8fc3844","html_url":"https://github.com/junyanz/light-field-video","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/junyanz/light-field-video","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junyanz%2Flight-field-video","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junyanz%2Flight-field-video/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junyanz%2Flight-field-video/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junyanz%2Flight-field-video/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/junyanz","download_url":"https://codeload.github.com/junyanz/light-field-video/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/junyanz%2Flight-field-video/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":264275925,"owners_count":23583332,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["caffe","computer-graphics","computer-vision","deep-learning","lightfield"],"created_at":"2024-10-03T10:37:45.537Z","updated_at":"2025-07-08T13:13:04.367Z","avatar_url":"https://github.com/junyanz.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Light Field Video Viewer\n\u003cimg src='imgs/demo.gif' width=480\u003e\n\n### [[Project]](http://cseweb.ucsd.edu/~viscomp/projects/LF/papers/SIG17/lfv/)  [[Video]](https://www.youtube.com/watch?time_continue=1\u0026v=TqVKcssYfAo) [[Paper]](http://cseweb.ucsd.edu/~viscomp/projects/LF/papers/SIG17/lfv/paperData/LF_video.pdf)  \n\nC++ implementation for Light field video applications (including video refocusing, focus tracking, changing aperture and view) as described in the following paper:\n\n\u003cimg src=\"imgs/teaser.jpg\" width=\"900px\"/\u003e\n\nLight Field Video Capture Using a Learning-Based Hybrid Imaging System  \n[Ting-Chun Wang](https://tcwang0509.github.io/), [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/), [Nima Khademi Kalantari](http://nkhademi.com/), [Alexei A. Efros](https://people.eecs.berkeley.edu/~efros/), and [Ravi Ramamoorthi](http://cseweb.ucsd.edu/~ravir/)  \nIn ACM Transactions on Graphics (SIGGRAPH 2017)\n\n### Prerequisites\n- Linux. (The code should work on OSX/Windows with minimal modification)\n- OpenMP, [OpenCV](http://milq.github.io/install-opencv-ubuntu-debian/), [QT 5.7](https://wiki.qt.io/Install_Qt_5_on_Ubuntu), [cmake](http://askubuntu.com/questions/610291/how-to-install-cmake-3-2-on-ubuntu-14-04).\n\n\n### Getting Started\n- Clone this repo:\n```bash\ngit clone https://github.com/junyanz/lfv_release.git lfv\ncd lfv\n```\n- Please modify line 5 in CMakeLists.txt to include the QT5 installation path.\n\n- Download light field video data (e.g. `cats`).\n```\nbash data/download_lfv.sh cats\n```\n- Compile the code:\n```bash\nmkdir cbuild\ncd cbuild\ncmake -DCMAKE_BUILD_TYPE=Release  ../\nmake\n```\n- Start the viewer:\n```bash\n./lfv --data_dir ../data/cats/ --scale 2.0\n```\n\n## Arguments:\n- `--data_dir`: the directory that stores light field video frames, and disparity maps\n- `--scale`: up-sample the image by `scale`.\n\n\n## User Interface\n\u003cimg src=\"imgs/ui.jpg\" width=\"600px\"/\u003e\n\nMouse Interaction\n- Refocusing: press + left click\n- View Change: move the mouse + right click\n\nControl Panel\n- Focal Plane: change the focal plane\n- Aperture: change the camera aperture\n- Focal Type: Fixed focal point or automatic tracking\n- Restart (`r`): restart the system\n- Play/Stop (`p`): play or pause the video\n- Quit (`q`): quit the program\n\nShortcuts:\n- Show/hide the focus point: `f`\n- Enable/disable tracking mode: `t`\n\n\n## Training/test [code](http://cseweb.ucsd.edu/~viscomp/projects/LF/papers/SIG17/lfv/paperData/LF_video_Code_v1.1.zip)\n\n## Light field videos:\nPlease use the script `bash data/download_lfv.sh video_name` to download the light field video from our website.  \n### cats\n\u003cimg src=\"imgs/cats.jpg\" width=\"256px\"/\u003e\n\n### train1\n\u003cimg src=\"imgs/train1.jpg\" width=\"256px\"/\u003e\n\n### train2\n\u003cimg src=\"imgs/train2.jpg\" width=\"256px\"/\u003e\n\n\n### dancing\n\u003cimg src=\"imgs/dancing.jpg\" width=\"256px\"/\u003e\n\n\n\n\n\n## Citation\nIf you use this code for your research, please cite our paper.\n```\n@article{wang2017light,\n    author  = {Ting-Chun Wang and Jun-Yan Zhu and Nima Khademi Kalantari and\n               Alexei A. Efros and Ravi Ramamoorthi},\n    title   = {Light Field Video Capture Using a Learning-Based Hybrid Imaging System},\n    journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH 2017)},\n    volume  = {36},\n    number  = {4},\n    year    = {2017},\n}\n```\n\n\n## Cat Paper Collection\nIf you love cats, and love reading cool graphics, vision, and learning papers, please check out the Cat Paper Collection:  \n[[Github]](https://github.com/junyanz/CatPapers) [[Webpage]](https://www.cs.cmu.edu/~junyanz/cat/cat_papers.html)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjunyanz%2Flight-field-video","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjunyanz%2Flight-field-video","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjunyanz%2Flight-field-video/lists"}