{"url":"/sota/optical-flow-estimation-on-sintel-clean","task":{"name":"Optical Flow Estimation","url":"/task/optical-flow-estimation","note":null},"dataset":{"name":"Sintel-clean","url":"/dataset/mpi-sintel"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Optical Flow Estimation** is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.\r\n\r\nApproaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.\r\n\r\nFurther readings:\r\n\r\n- [Optical Flow Estimation](https://www.cs.toronto.edu/~fleet/research/Papers/flowChapter05.pdf)\r\n- [Performance of Optical Flow Techniques](https://www.cs.toronto.edu/~fleet/research/Papers/ijcv-94.pdf)\r\n\r\nDefinition source: [Devon: Deformable Volume Network for Learning Optical Flow ](https://arxiv.org/abs/1802.07351)\r\n\r\nImage credit: [Optical Flow Estimation](https://www.cs.toronto.edu/~fleet/research/Papers/flowChapter05.pdf)","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":["Average End-Point Error"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average End-Point Error":"lower"}},"counts":{"rows":29,"rows_with_code":26,"rows_with_paper_page":29,"rows_dated":29,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MEMFOF-L","metrics":{"Average End-Point Error":"0.963"},"uses_additional_data":false,"paper_date":"2025-06-29","paper":"/paper/memfof-high-resolution-training-for-memory","paper_url":"https://arxiv.org/abs/2506.23151v1","paper_title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","code":"https://github.com/msu-video-group/memfof","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"GMFlow","metrics":{"Average End-Point Error":"1.03"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/unifying-flow-stereo-and-depth-estimation","paper_url":"https://arxiv.org/abs/2211.05783v3","paper_title":"Unifying Flow, Stereo and Depth Estimation","code":"https://github.com/autonomousvision/unimatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"DPFlow","metrics":{"Average End-Point Error":"1.046"},"uses_additional_data":false,"paper_date":"2025-03-19","paper":"/paper/dpflow-adaptive-optical-flow-estimation-with-1","paper_url":"https://arxiv.org/abs/2503.14880v1","paper_title":"DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework","code":"https://github.com/hmorimitsu/ptlflow","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CroCo-Flow","metrics":{"Average End-Point Error":"1.092"},"uses_additional_data":false,"paper_date":"2022-11-18","paper":"/paper/improved-cross-view-completion-pre-training","paper_url":"https://arxiv.org/abs/2211.10408v3","paper_title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","code":"https://github.com/naver/croco","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"FlowFormer","metrics":{"Average End-Point Error":"1.16"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/flowformer-a-transformer-architecture-for","paper_url":"https://arxiv.org/abs/2203.16194v4","paper_title":"FlowFormer: A Transformer Architecture for Optical Flow","code":"https://github.com/drinkingcoder/FlowFormer-Official","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Ef-RAFT","metrics":{"Average End-Point Error":"1.27"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/rethinking-raft-for-efficient-optical-flow","paper_url":"https://arxiv.org/abs/2401.00833v1","paper_title":"Rethinking RAFT for Efficient Optical Flow","code":"https://github.com/n3slami/Ef-RAFT","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"RPKNet","metrics":{"Average End-Point Error":"1.315"},"uses_additional_data":false,"paper_date":"2024-02-01","paper":"/paper/recurrent-partial-kernel-network-for","paper_url":"https://hmorimitsu.com/publication/2024-aaai-rpknet/","paper_title":"Recurrent Partial Kernel Network for Efficient Optical Flow Estimation","code":"https://github.com/hmorimitsu/ptlflow","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"GMA","metrics":{"Average End-Point Error":"1.388"},"uses_additional_data":false,"paper_date":"2021-04-06","paper":"/paper/learning-to-estimate-hidden-motions-with","paper_url":"https://arxiv.org/abs/2104.02409v3","paper_title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","code":"https://github.com/open-mmlab/mmflow","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"GMFlowNet","metrics":{"Average End-Point Error":"1.390"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/global-matching-with-overlapping-attention","paper_url":"https://arxiv.org/abs/2203.11335v1","paper_title":"Global Matching with Overlapping Attention for Optical Flow Estimation","code":"https://github.com/xiaofeng94/gmflownet","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"DEQ-Flow-H","metrics":{"Average End-Point Error":"1.519"},"uses_additional_data":false,"paper_date":"2022-04-18","paper":"/paper/deep-equilibrium-optical-flow-estimation","paper_url":"https://arxiv.org/abs/2204.08442v1","paper_title":"Deep Equilibrium Optical Flow Estimation","code":"https://github.com/locuslab/deq-flow","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"RAFT (warm-start)","metrics":{"Average End-Point Error":"1.609"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/raft-recurrent-all-pairs-field-transforms-for","paper_url":"https://arxiv.org/abs/2003.12039v3","paper_title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","code":"https://github.com/pytorch/vision","n_code_links":17,"syntology":{"n_ran":40,"n_unverified":26,"n_samples":66,"n_pointer_only_licence":17}},{"rank_in_archive_order":12,"model":"Perceiver IO","metrics":{"Average End-Point Error":"1.81"},"uses_additional_data":false,"paper_date":"2021-07-30","paper":"/paper/perceiver-io-a-general-architecture-for","paper_url":"https://arxiv.org/abs/2107.14795v3","paper_title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"RAPIDFlow","metrics":{"Average End-Point Error":"2.03"},"uses_additional_data":false,"paper_date":"2024-05-01","paper":"/paper/rapidflow-recurrent-adaptable-pyramids-with","paper_url":"https://hmorimitsu.com/publication/2024-icra-rapidflow/","paper_title":"RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation","code":"https://github.com/hmorimitsu/ptlflow","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"MaskFlownet","metrics":{"Average End-Point Error":"2.52"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/maskflownet-asymmetric-feature-matching-with","paper_url":"https://arxiv.org/abs/2003.10955v2","paper_title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","code":"https://github.com/open-mmlab/mmflow","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"MR-Flow","metrics":{"Average End-Point Error":"2.53"},"uses_additional_data":false,"paper_date":"2017-05-03","paper":"/paper/optical-flow-in-mostly-rigid-scenes","paper_url":"http://arxiv.org/abs/1705.01352v1","paper_title":"Optical Flow in Mostly Rigid Scenes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"MaskFlownet-S","metrics":{"Average End-Point Error":"2.77"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/maskflownet-asymmetric-feature-matching-with","paper_url":"https://arxiv.org/abs/2003.10955v2","paper_title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","code":"https://github.com/open-mmlab/mmflow","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"ProFlow+ft","metrics":{"Average End-Point Error":"2.82"},"uses_additional_data":false,"paper_date":"2018-06-03","paper":"/paper/proflow-learning-to-predict-optical-flow","paper_url":"http://arxiv.org/abs/1806.00800v1","paper_title":"ProFlow: Learning to Predict Optical Flow","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"LiteFlowNet3","metrics":{"Average End-Point Error":"2.99"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/liteflownet3-resolving-correspondence","paper_url":"https://arxiv.org/abs/2007.09319v1","paper_title":"LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation","code":"https://github.com/twhui/LiteFlowNet3","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"LiteFlowNet3-S","metrics":{"Average End-Point Error":"3.03"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/liteflownet3-resolving-correspondence","paper_url":"https://arxiv.org/abs/2007.09319v1","paper_title":"LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation","code":"https://github.com/twhui/LiteFlowNet3","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"LiteFlowNet2-ft","metrics":{"Average End-Point Error":"3.48"},"uses_additional_data":false,"paper_date":"2019-03-15","paper":"/paper/a-lightweight-optical-flow-cnn-revisiting","paper_url":"https://arxiv.org/abs/1903.07414v3","paper_title":"A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization","code":"https://github.com/open-mmlab/mmflow","n_code_links":3,"syntology":null},{"rank_in_archive_order":21,"model":"ScopeFlow","metrics":{"Average End-Point Error":"3.592"},"uses_additional_data":false,"paper_date":"2020-02-25","paper":"/paper/scopeflow-dynamic-scene-scoping-for-optical","paper_url":"https://arxiv.org/abs/2002.10770v2","paper_title":"ScopeFlow: Dynamic Scene Scoping for Optical Flow","code":"https://github.com/avirambh/ScopeFlow","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"FDFlowNet-ft","metrics":{"Average End-Point Error":"3.71"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/fdflownet-fast-optical-flow-estimation-using","paper_url":"https://arxiv.org/abs/2006.12263v1","paper_title":"FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"SelFlow","metrics":{"Average End-Point Error":"3.74"},"uses_additional_data":false,"paper_date":"2019-04-19","paper":"/paper/selflow-self-supervised-learning-of-optical","paper_url":"http://arxiv.org/abs/1904.09117v1","paper_title":"SelFlow: Self-Supervised Learning of Optical Flow","code":"https://github.com/ppliuboy/SelFlow","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"IRR-PWC","metrics":{"Average End-Point Error":"3.84"},"uses_additional_data":false,"paper_date":"2019-04-10","paper":"/paper/iterative-residual-refinement-for-joint","paper_url":"http://arxiv.org/abs/1904.05290v1","paper_title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","code":"https://github.com/open-mmlab/mmflow","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"FlowNet2","metrics":{"Average End-Point Error":"3.96"},"uses_additional_data":false,"paper_date":"2016-12-06","paper":"/paper/flownet-20-evolution-of-optical-flow","paper_url":"http://arxiv.org/abs/1612.01925v1","paper_title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","code":"https://github.com/NVIDIA/flownet2-pytorch","n_code_links":12,"syntology":{"n_ran":2,"n_unverified":19,"n_samples":21,"n_pointer_only_licence":3}},{"rank_in_archive_order":26,"model":"LiteFlowNet-ft","metrics":{"Average End-Point Error":"4.54"},"uses_additional_data":false,"paper_date":"2018-05-18","paper":"/paper/liteflownet-a-lightweight-convolutional","paper_url":"http://arxiv.org/abs/1805.07036v1","paper_title":"LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation","code":"https://github.com/open-mmlab/mmflow","n_code_links":4,"syntology":null},{"rank_in_archive_order":27,"model":"UnrolledCost","metrics":{"Average End-Point Error":"4.69"},"uses_additional_data":false,"paper_date":"2020-11-30","paper":"/paper/unsupervised-optical-flow-using-cost-function","paper_url":"https://arxiv.org/abs/2011.14814v3","paper_title":"Cost Function Unrolling in Unsupervised Optical Flow","code":"https://github.com/gallif/costfunctionunrolling","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"FastFlowNet-ft","metrics":{"Average End-Point Error":"4.89"},"uses_additional_data":false,"paper_date":"2021-03-08","paper":"/paper/fastflownet-a-lightweight-network-for-fast","paper_url":"https://arxiv.org/abs/2103.04524v2","paper_title":"FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation","code":"https://github.com/ltkong218/FastFlowNet","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":29,"model":"Spynet","metrics":{"Average End-Point Error":"6.64"},"uses_additional_data":false,"paper_date":"2016-11-03","paper":"/paper/optical-flow-estimation-using-a-spatial","paper_url":"http://arxiv.org/abs/1611.00850v2","paper_title":"Optical Flow Estimation using a Spatial Pyramid Network","code":"https://github.com/philferriere/tfoptflow","n_code_links":8,"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":12,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":69,"n_unverified":98,"n_samples":167,"n_pointer_only_licence":23,"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":109,"n_samples":178,"n_pointer_only_licence":23,"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"}}}