{"url":"/sota/video-frame-interpolation-on-ucf101-1","task":{"name":"Video Frame Interpolation","url":"/task/video-frame-interpolation","note":null},"dataset":{"name":"UCF101","url":"/dataset/ucf101"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The goal of **Video Frame Interpolation** is to synthesize several frames in the middle of two adjacent frames of the original video. Video Frame Interpolation can be applied to generate slow motion video, increase video frame rate, and frame recovery in video streaming.\r\n\r\n\r\n<span class=\"description-source\">Source: [Reducing the X-ray radiation exposure frequency in cardio-angiography via deep-learning based video interpolation ](https://arxiv.org/abs/2006.00781)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["PSNR","SSIM","PSNR (sRGB)","LPIPS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PSNR":"higher","SSIM":"higher","PSNR (sRGB)":"higher","LPIPS":null}},"counts":{"rows":19,"rows_with_code":17,"rows_with_paper_page":19,"rows_dated":19,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"EMA-VFI","metrics":{"PSNR":"35.48","SSIM":"0.9701"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/extracting-motion-and-appearance-via-inter","paper_url":"https://arxiv.org/abs/2303.00440v2","paper_title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","code":"https://github.com/mcg-nju/ema-vfi","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"UPR-Net LARGE","metrics":{"PSNR":"35.47","SSIM":"0.9700"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/a-unified-pyramid-recurrent-network-for-video","paper_url":"https://arxiv.org/abs/2211.03456v2","paper_title":"A Unified Pyramid Recurrent Network for Video Frame Interpolation","code":"https://github.com/srcn-ivl/upr-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"VFIMamba","metrics":{"PSNR":"35.45","SSIM":"0.9702"},"uses_additional_data":false,"paper_date":"2024-07-02","paper":"/paper/vfimamba-video-frame-interpolation-with-state","paper_url":"https://arxiv.org/abs/2407.02315v2","paper_title":"VFIMamba: Video Frame Interpolation with State Space Models","code":"https://github.com/mcg-nju/vfimamba","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"DQBC","metrics":{"PSNR":"35.44","SSIM":"0.9700"},"uses_additional_data":false,"paper_date":"2023-04-26","paper":"/paper/video-frame-interpolation-with-densely","paper_url":"https://arxiv.org/abs/2304.13596v1","paper_title":"Video Frame Interpolation with Densely Queried Bilateral Correlation","code":"https://github.com/kinoud/DQBC","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MA-CSPA","metrics":{"PSNR":"35.43","SSIM":"0.979"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/exploring-motion-ambiguity-and-alignment-for","paper_url":"https://arxiv.org/abs/2203.10291v1","paper_title":"Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"IFRNet","metrics":{"PSNR":"35.42","SSIM":"0.9698"},"uses_additional_data":false,"paper_date":"2022-05-29","paper":"/paper/ifrnet-intermediate-feature-refine-network","paper_url":"https://arxiv.org/abs/2205.14620v1","paper_title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","code":"https://github.com/ltkong218/ifrnet","n_code_links":2,"syntology":{"n_ran":17,"n_unverified":3,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"EBME-H*","metrics":{"PSNR":"35.41","SSIM":"0.970"},"uses_additional_data":false,"paper_date":"2022-06-17","paper":"/paper/enhanced-bi-directional-motion-estimation-for","paper_url":"https://arxiv.org/abs/2206.08572v3","paper_title":"Enhanced Bi-directional Motion Estimation for Video Frame Interpolation","code":"https://github.com/srcn-ivl/ebme","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SoftSplat","metrics":{"PSNR":"35.39","SSIM":"0.952"},"uses_additional_data":false,"paper_date":"2020-03-11","paper":"/paper/softmax-splatting-for-video-frame","paper_url":"https://arxiv.org/abs/2003.05534v1","paper_title":"Softmax Splatting for Video Frame Interpolation","code":"https://github.com/sniklaus/softmax-splatting","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"ABME","metrics":{"PSNR":"35.38","SSIM":"0.9698"},"uses_additional_data":false,"paper_date":"2021-08-15","paper":"/paper/asymmetric-bilateral-motion-estimation-for","paper_url":"https://arxiv.org/abs/2108.06815v1","paper_title":"Asymmetric Bilateral Motion Estimation for Video Frame Interpolation","code":"https://github.com/junheum/abme","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":11,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"CURE","metrics":{"PSNR":"35.36","SSIM":"0.9705"},"uses_additional_data":false,"paper_date":"2022-02-28","paper":"/paper/learning-cross-video-neural-representations","paper_url":"https://arxiv.org/abs/2203.00137v1","paper_title":"Learning Cross-Video Neural Representations for High-Quality Frame Interpolation","code":"https://github.com/wustl-cig/CURE","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"NCM-Base","metrics":{"PSNR":"35.36","SSIM":"0.9695"},"uses_additional_data":false,"paper_date":"2022-07-14","paper":"/paper/neighbor-correspondence-matching-for-flow","paper_url":"https://arxiv.org/abs/2207.06763v1","paper_title":"Neighbor Correspondence Matching for Flow-based Video Frame Synthesis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"FILM","metrics":{"PSNR":"35.32","SSIM":"0.952"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/film-frame-interpolation-for-large-motion","paper_url":"https://arxiv.org/abs/2202.04901v4","paper_title":"FILM: Frame Interpolation for Large Motion","code":"https://github.com/google-research/frame-interpolation","n_code_links":2,"syntology":{"n_ran":12,"n_unverified":8,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"CDFI","metrics":{"LPIPS":"0.015","PSNR":"35.21"},"uses_additional_data":false,"paper_date":"2021-03-18","paper":"/paper/cdfi-compression-driven-network-design-for","paper_url":"https://arxiv.org/abs/2103.10559v2","paper_title":"CDFI: Compression-Driven Network Design for Frame Interpolation","code":"https://github.com/tding1/CDFI","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"M2M-PWC","metrics":{"PSNR":"35.17","SSIM":"0.97"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/many-to-many-splatting-for-efficient-video","paper_url":"https://arxiv.org/abs/2204.03513v1","paper_title":"Many-to-many Splatting for Efficient Video Frame Interpolation","code":"https://github.com/feinanshan/m2m_vfi","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"BMBC","metrics":{"PSNR":"35.15","SSIM":"0.9689"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/bmbc-bilateral-motion-estimation-with","paper_url":"https://arxiv.org/abs/2007.12622v1","paper_title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","code":"https://github.com/JunHeum/BMBC","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"DAIN","metrics":{"PSNR":"34.99","SSIM":"0.9683"},"uses_additional_data":false,"paper_date":"2019-04-01","paper":"/paper/depth-aware-video-frame-interpolation","paper_url":"http://arxiv.org/abs/1904.00830v1","paper_title":"Depth-Aware Video Frame Interpolation","code":"https://github.com/baowenbo/DAIN","n_code_links":5,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"RRIN","metrics":{"PSNR":"34.93","SSIM":"0.9496"},"uses_additional_data":false,"paper_date":"2020-05-04","paper":"/paper/video-frame-interpolation-via-residue","paper_url":"https://ieeexplore.ieee.org/document/9053987","paper_title":"Video Frame Interpolation via Residue Refinement","code":"https://github.com/HopLee6/RRIN","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"ST-MFNet","metrics":{"PSNR":"33.384"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/spatio-temporal-multi-flow-network-for-video","paper_url":"https://arxiv.org/abs/2111.15483v2","paper_title":"ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation","code":"https://github.com/danier97/st-mfnet","n_code_links":3,"syntology":null},{"rank_in_archive_order":19,"model":"CycleSuperSloMo","metrics":{"PSNR (sRGB)":"34.55"},"uses_additional_data":false,"paper_date":"2019-06-13","paper":"/paper/unsupervised-video-interpolation-using-cycle","paper_url":"https://arxiv.org/abs/1906.05928v3","paper_title":"Unsupervised Video Interpolation Using Cycle Consistency","code":"https://github.com/NVIDIA/unsupervised-video-interpolation","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":10,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":69,"n_unverified":47,"n_samples":116,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":69,"n_unverified":47,"n_samples":116,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}