{"id":19932257,"url":"https://github.com/amazon-science/small-baseline-camera-tracking","last_synced_at":"2026-03-03T20:32:57.390Z","repository":{"id":49334361,"uuid":"472445975","full_name":"amazon-science/small-baseline-camera-tracking","owner":"amazon-science","description":"A dataset to facilitate the research of Structure-from-Motion (SfM) for movie and TV shows.","archived":false,"fork":false,"pushed_at":"2023-02-16T22:53:21.000Z","size":1582,"stargazers_count":71,"open_issues_count":0,"forks_count":6,"subscribers_count":9,"default_branch":"main","last_synced_at":"2025-09-09T05:11:48.295Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/amazon-science.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2022-03-21T17:37:58.000Z","updated_at":"2025-06-17T03:52:55.000Z","dependencies_parsed_at":"2025-01-18T22:47:00.188Z","dependency_job_id":null,"html_url":"https://github.com/amazon-science/small-baseline-camera-tracking","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/amazon-science/small-baseline-camera-tracking","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fsmall-baseline-camera-tracking","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fsmall-baseline-camera-tracking/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fsmall-baseline-camera-tracking/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fsmall-baseline-camera-tracking/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/amazon-science","download_url":"https://codeload.github.com/amazon-science/small-baseline-camera-tracking/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fsmall-baseline-camera-tracking/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30058292,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T18:21:05.932Z","status":"ssl_error","status_checked_at":"2026-03-03T18:20:59.341Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2024-11-12T23:09:31.176Z","updated_at":"2026-03-03T20:32:57.345Z","avatar_url":"https://github.com/amazon-science.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"## Small-Baseline Camera-Tracking Dataset\n\n![image info](./example.png)\n\nWe present the Small-Baseline Camera-Tracking dataset which is used as the evaluation dataset (StudioSfM) in the following paper:\n\n\u003cem\u003eDepth-Guided Sparse Structure-from-Motion for Movies and TV Shows\u003c/em\u003e. Sheng Liu, Xiaohan Nie, Raffay Hamid, IEEE CVPR 2022\n\n\nThis dataset contains 130 video shots collected from 15 TV episodes from Amazon Prime Video. Each shot is annotated with corresponding camera motion data by a professional CG studio. This dataset aims to faciliate the research of 3D reconstruction for small-baseline videos in movies and TV shows.\n\n### Annotation\n\nIn the folder of each video, the camera motion data is stored as a dictionary in 'camera.pkl' file which can be loaded using pickle package with Python 3.7. \n\nThe key of the dictionary is the image id which corresponds to image name, and the value is also a dictionary with 'intr_mtx' stores the camera intrinsics and 'v2c' stores the world to camera transformation. \n\n### How to request the download link\nPlease contact shenlu *at* amazon.com to request the download link of the full dataset. \n\n## License\n\nThis repository is licensed under the CC-BY-NC 4.0 License.\n\n## Citation\n\nIf you use this dataset, please cite the following paper:\n\n```\n@inproceedings{pv-2022-sfm,\n    title = \"Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows\",\n    author = \"Sheng Liu  and\n      Xiaohan Nie  and\n      Raffay Hamid\",\n    booktitle = \"The Conference on Computer Vision and Pattern Recognition\",\n    year = \"2022\",\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famazon-science%2Fsmall-baseline-camera-tracking","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famazon-science%2Fsmall-baseline-camera-tracking","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famazon-science%2Fsmall-baseline-camera-tracking/lists"}