{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","arxiv_id":"1702.02463","date":"2017-02-08","proceeding":"ICCV 2017 10","authors":["Ziwei Liu","Raymond A. Yeh","Xiaoou Tang","Yiming Liu","Aseem Agarwala"],"abstract":"We address the problem of synthesizing new video frames in an existing video,\neither in-between existing frames (interpolation), or subsequent to them\n(extrapolation). This problem is challenging because video appearance and\nmotion can be highly complex. Traditional optical-flow-based solutions often\nfail where flow estimation is challenging, while newer neural-network-based\nmethods that hallucinate pixel values directly often produce blurry results. We\ncombine the advantages of these two methods by training a deep network that\nlearns to synthesize video frames by flowing pixel values from existing ones,\nwhich we call deep voxel flow. Our method requires no human supervision, and\nany video can be used as training data by dropping, and then learning to\npredict, existing frames. The technique is efficient, and can be applied at any\nvideo resolution. We demonstrate that our method produces results that both\nquantitatively and qualitatively improve upon the state-of-the-art.","url_abs":"http://arxiv.org/abs/1702.02463v2","url_pdf":"http://arxiv.org/pdf/1702.02463v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"video-frame-synthesis-using-deep-voxel-flow","repo_url":"https://github.com/NVIDIA/unsupervised-video-interpolation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"video-frame-synthesis-using-deep-voxel-flow","repo_url":"https://github.com/liuziwei7/voxel-flow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"video-frame-synthesis-using-deep-voxel-flow","repo_url":"https://github.com/lxx1991/pytorch-voxel-flow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-prediction-on-cityscapes-1","task":"Video Prediction","dataset":"Cityscapes","model":"DVF","rank_in_archive_order":3,"of":3,"metrics":{"LPIPS":"0.1737","MS-SSIM":"0.8350"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-davis-2017","task":"Video Prediction","dataset":"DAVIS 2017","model":"DVF","rank_in_archive_order":2,"of":2,"metrics":{"LPIPS":"0.2323","MS-SSIM":"0.6861"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-kitti","task":"Video Prediction","dataset":"KITTI","model":"DVF","rank_in_archive_order":3,"of":3,"metrics":{"LPIPS":"0.3247","MS-SSIM":"0.5393"},"uses_additional_data":false},{"leaderboard":"/sota/video-prediction-on-vimeo90k","task":"Video Prediction","dataset":"Vimeo90K","model":"DVF","rank_in_archive_order":3,"of":3,"metrics":{"LPIPS":"0.0773","MS-SSIM":"0.9211"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1702.02463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02463"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuziwei7/voxel-flow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NVIDIA/unsupervised-video-interpolation","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lxx1991/pytorch-voxel-flow","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"0bcee60a90a51b11","entry":"meshgrid","repo":"lxx1991/pytorch-voxel-flow","repo_kind":"listed","path":"core/models/voxel_flow.py","file_url":"https://github.com/lxx1991/pytorch-voxel-flow/blob/HEAD/core/models/voxel_flow.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0bcee60a90a51b11"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}