{"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/xvfi-extreme-video-frame-interpolation","title":"XVFI: eXtreme Video Frame Interpolation","arxiv_id":"2103.16206","date":"2021-03-30","proceeding":"ICCV 2021 10","authors":["Hyeonjun Sim","Jihyong Oh","Munchurl Kim"],"abstract":"In this paper, we firstly present a dataset (X4K1000FPS) of 4K videos of 1000 fps with the extreme motion to the research community for video frame interpolation (VFI), and propose an extreme VFI network, called XVFI-Net, that first handles the VFI for 4K videos with large motion. The XVFI-Net is based on a recursive multi-scale shared structure that consists of two cascaded modules for bidirectional optical flow learning between two input frames (BiOF-I) and for bidirectional optical flow learning from target to input frames (BiOF-T). The optical flows are stably approximated by a complementary flow reversal (CFR) proposed in BiOF-T module. During inference, the BiOF-I module can start at any scale of input while the BiOF-T module only operates at the original input scale so that the inference can be accelerated while maintaining highly accurate VFI performance. Extensive experimental results show that our XVFI-Net can successfully capture the essential information of objects with extremely large motions and complex textures while the state-of-the-art methods exhibit poor performance. Furthermore, our XVFI-Net framework also performs comparably on the previous lower resolution benchmark dataset, which shows a robustness of our algorithm as well. All source codes, pre-trained models, and proposed X4K1000FPS datasets are publicly available at https://github.com/JihyongOh/XVFI.","url_abs":"https://arxiv.org/abs/2103.16206v2","url_pdf":"https://arxiv.org/pdf/2103.16206v2.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":"xvfi-extreme-video-frame-interpolation","repo_url":"https://github.com/JihyongOh/XVFI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"},{"task_slug":"extreme-video-frame-interpolation","task_name":"eXtreme-Video-Frame-Interpolation"}],"methods":[],"datasets_introduced":[{"slug":"x4k1000fps","name":"X4K1000FPS","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-frame-interpolation-on-msu-video-frame","task":"Video Frame Interpolation","dataset":"MSU Video Frame Interpolation","model":"XVFI (S_{tst}=3)","rank_in_archive_order":2,"of":24,"metrics":{"FPS":"5.4","LPIPS":"0.061","MS-SSIM":"0.933","PSNR":"27.35","SSIM":"0.913","Subjective score":"1.38","VMAF":"63.47"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-msu-video-frame","task":"Video Frame Interpolation","dataset":"MSU Video Frame Interpolation","model":"XVFI (S_{tst}=5)","rank_in_archive_order":14,"of":24,"metrics":{"LPIPS":"0.049","MS-SSIM":"0.955","PSNR":"27.86","SSIM":"0.921","VMAF":"67.25"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-vimeo90k","task":"Video Frame Interpolation","dataset":"Vimeo90K","model":"XVFI","rank_in_archive_order":15,"of":23,"metrics":{"PSNR":"35.07","SSIM":"0.9760"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps","task":"Video Frame Interpolation","dataset":"X4K1000FPS","model":"XVFI-Net (S_{tst}=5)","rank_in_archive_order":12,"of":20,"metrics":{"PSNR":"30.12","SSIM":"0.870","tOF":"2.15"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps","task":"Video Frame Interpolation","dataset":"X4K1000FPS","model":"XVFI-Net (S_{tst}=3)","rank_in_archive_order":14,"of":20,"metrics":{"PSNR":"28.86","SSIM":"0.858","tOF":"2.67"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2103.16206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16206"}},"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":"deterministic:regex_extraction","url":"https://github.com/JihyongOh/XVFI","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"8cf266f1451fe98e","entry":"RResBlock2D_3D","repo":"JihyongOh/XVFI","repo_kind":"official","path":"XVFInet.py","file_url":"https://github.com/JihyongOh/XVFI/blob/HEAD/XVFInet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8cf266f1451fe98e"}},{"code_sha256_prefix":"fb511b095f9ec48c","entry":"RefineUNet","repo":"JihyongOh/XVFI","repo_kind":"official","path":"XVFInet.py","file_url":"https://github.com/JihyongOh/XVFI/blob/HEAD/XVFInet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb511b095f9ec48c"}},{"code_sha256_prefix":"f9280b07c95bf180","entry":"ResBlock2D_3D","repo":"JihyongOh/XVFI","repo_kind":"official","path":"XVFInet.py","file_url":"https://github.com/JihyongOh/XVFI/blob/HEAD/XVFInet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9280b07c95bf180"}},{"code_sha256_prefix":"47e37743b63033e0","entry":"VFInet","repo":"JihyongOh/XVFI","repo_kind":"official","path":"XVFInet.py","file_url":"https://github.com/JihyongOh/XVFI/blob/HEAD/XVFInet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47e37743b63033e0"}},{"code_sha256_prefix":"0efc370fbd2bf248","entry":"XVFInet","repo":"JihyongOh/XVFI","repo_kind":"official","path":"XVFInet.py","file_url":"https://github.com/JihyongOh/XVFI/blob/HEAD/XVFInet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0efc370fbd2bf248"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}