{"task":"Optical Flow Estimation","dataset":"Sintel-final","metric_names":["Average End-Point Error"],"rows":[{"id":52670,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"MEMFOF-L","metrics":{"Average End-Point Error":"1.907"},"paper_url":"https://arxiv.org/abs/2506.23151v1","paper_title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","paper_date":"2025-06-29","code_links":[{"title":"msu-video-group/memfof","url":"https://github.com/msu-video-group/memfof"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52671,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"DPFlow","metrics":{"Average End-Point Error":"1.975"},"paper_url":"https://arxiv.org/abs/2503.14880v1","paper_title":"DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework","paper_date":"2025-03-19","code_links":[{"title":"hmorimitsu/ptlflow","url":"https://github.com/hmorimitsu/ptlflow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52672,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"GMFlow","metrics":{"Average End-Point Error":"2.37"},"paper_url":"https://arxiv.org/abs/2211.05783v3","paper_title":"Unifying Flow, Stereo and Depth Estimation","paper_date":"2022-11-10","code_links":[{"title":"autonomousvision/unimatch","url":"https://github.com/autonomousvision/unimatch"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52673,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"Perceiver IO","metrics":{"Average End-Point Error":"2.42"},"paper_url":"https://arxiv.org/abs/2107.14795v3","paper_title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","paper_date":"2021-07-30","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"deepmind/deepmind-research","url":"https://github.com/deepmind/deepmind-research/tree/master/perceiver"},{"title":"lucidrains/perceiver-pytorch","url":"https://github.com/lucidrains/perceiver-pytorch"},{"title":"krasserm/perceiver-io","url":"https://github.com/krasserm/perceiver-io"},{"title":"SforAiDl/vformer","url":"https://github.com/SforAiDl/vformer"},{"title":"esceptico/perceiver-io","url":"https://github.com/esceptico/perceiver-io"},{"title":"2796gaurav/code_examples","url":"https://github.com/2796gaurav/code_examples/tree/main/Perceiver"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/perceiver"},{"title":"MindSpore-scientific-2/code-7","url":"https://github.com/MindSpore-scientific-2/code-7/tree/main/SISDTA"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52674,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"CroCo-Flow","metrics":{"Average End-Point Error":"2.436"},"paper_url":"https://arxiv.org/abs/2211.10408v3","paper_title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","paper_date":"2022-11-18","code_links":[{"title":"naver/croco","url":"https://github.com/naver/croco"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52675,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"GMA","metrics":{"Average End-Point Error":"2.470"},"paper_url":"https://arxiv.org/abs/2104.02409v3","paper_title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","paper_date":"2021-04-06","code_links":[{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"zacjiang/GMA","url":"https://github.com/zacjiang/GMA"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52676,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"Ef-RAFT","metrics":{"Average End-Point Error":"2.60"},"paper_url":"https://arxiv.org/abs/2401.00833v1","paper_title":"Rethinking RAFT for Efficient Optical Flow","paper_date":"2024-01-01","code_links":[{"title":"n3slami/Ef-RAFT","url":"https://github.com/n3slami/Ef-RAFT"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52677,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"GMFlowNet","metrics":{"Average End-Point Error":"2.648"},"paper_url":"https://arxiv.org/abs/2203.11335v1","paper_title":"Global Matching with Overlapping Attention for Optical Flow Estimation","paper_date":"2022-03-21","code_links":[{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52678,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"RPKNet","metrics":{"Average End-Point Error":"2.657"},"paper_url":"https://hmorimitsu.com/publication/2024-aaai-rpknet/","paper_title":"Recurrent Partial Kernel Network for Efficient Optical Flow Estimation","paper_date":"2024-02-01","code_links":[{"title":"hmorimitsu/ptlflow","url":"https://github.com/hmorimitsu/ptlflow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52679,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"RAFT (warm-start)","metrics":{"Average End-Point Error":"2.855"},"paper_url":"https://arxiv.org/abs/2003.12039v3","paper_title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","paper_date":"2020-03-26","code_links":[{"title":"pytorch/vision","url":"https://github.com/pytorch/vision"},{"title":"princeton-vl/RAFT","url":"https://github.com/princeton-vl/RAFT"},{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"ykasten/layered-neural-atlases","url":"https://github.com/ykasten/layered-neural-atlases"},{"title":"neu-vig/ezflow","url":"https://github.com/neu-vig/ezflow"},{"title":"neu-vi/ezflow","url":"https://github.com/neu-vi/ezflow"},{"title":"Visual-Behavior/aloception","url":"https://github.com/Visual-Behavior/aloception"},{"title":"plusgood-steven/id-blau","url":"https://github.com/plusgood-steven/id-blau"},{"title":"duke-vision/optical-flow-active-learning-release","url":"https://github.com/duke-vision/optical-flow-active-learning-release"},{"title":"ToyotaResearchInstitute/att-aware","url":"https://github.com/ToyotaResearchInstitute/att-aware"},{"title":"osmr/pytorchcv","url":"https://github.com/osmr/pytorchcv"},{"title":"wpr1018001/rethinking-low-quality-optical-flow","url":"https://github.com/wpr1018001/rethinking-low-quality-optical-flow"},{"title":"esakak/sevc","url":"https://github.com/esakak/sevc"},{"title":"aliciachenw/PIPsUS","url":"https://github.com/aliciachenw/PIPsUS"},{"title":"hpcforge/raft","url":"https://github.com/hpcforge/raft"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/RAF-ms-main"},{"title":"yangyucheng000/MSpaper","url":"https://github.com/yangyucheng000/MSpaper/tree/main/ViG"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52680,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"DEQ-Flow-H","metrics":{"Average End-Point Error":"2.886"},"paper_url":"https://arxiv.org/abs/2204.08442v1","paper_title":"Deep Equilibrium Optical Flow Estimation","paper_date":"2022-04-18","code_links":[{"title":"locuslab/deq-flow","url":"https://github.com/locuslab/deq-flow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52681,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"RAPIDFlow","metrics":{"Average End-Point Error":"3.56"},"paper_url":"https://hmorimitsu.com/publication/2024-icra-rapidflow/","paper_title":"RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation","paper_date":"2024-05-01","code_links":[{"title":"hmorimitsu/ptlflow","url":"https://github.com/hmorimitsu/ptlflow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52682,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"ScopeFlow","metrics":{"Average End-Point Error":"4.098"},"paper_url":"https://arxiv.org/abs/2002.10770v2","paper_title":"ScopeFlow: Dynamic Scene Scoping for Optical Flow","paper_date":"2020-02-25","code_links":[{"title":"avirambh/ScopeFlow","url":"https://github.com/avirambh/ScopeFlow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52683,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"MaskFlownet","metrics":{"Average End-Point Error":"4.17"},"paper_url":"https://arxiv.org/abs/2003.10955v2","paper_title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","paper_date":"2020-03-24","code_links":[{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"microsoft/MaskFlownet","url":"https://github.com/microsoft/MaskFlownet"},{"title":"AMatusV/MaskFlownet-ROS","url":"https://github.com/AMatusV/MaskFlownet-ROS"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52684,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"SelFlow","metrics":{"Average End-Point Error":"4.26"},"paper_url":"http://arxiv.org/abs/1904.09117v1","paper_title":"SelFlow: Self-Supervised Learning of Optical Flow","paper_date":"2019-04-19","code_links":[{"title":"ppliuboy/SelFlow","url":"https://github.com/ppliuboy/SelFlow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52685,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"MaskFlownet-S","metrics":{"Average End-Point Error":"4.38"},"paper_url":"https://arxiv.org/abs/2003.10955v2","paper_title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","paper_date":"2020-03-24","code_links":[{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"microsoft/MaskFlownet","url":"https://github.com/microsoft/MaskFlownet"},{"title":"AMatusV/MaskFlownet-ROS","url":"https://github.com/AMatusV/MaskFlownet-ROS"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52686,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"VCN","metrics":{"Average End-Point Error":"4.40"},"paper_url":"http://papers.nips.cc/paper/8367-volumetric-correspondence-networks-for-optical-flow","paper_title":"Volumetric Correspondence Networks for Optical Flow","paper_date":"2019-12-01","code_links":[{"title":"gengshan-y/VCN","url":"https://github.com/gengshan-y/VCN"},{"title":"neu-vig/ezflow","url":"https://github.com/neu-vig/ezflow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52687,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"LiteFlowNet3","metrics":{"Average End-Point Error":"4.45"},"paper_url":"https://arxiv.org/abs/2007.09319v1","paper_title":"LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation","paper_date":"2020-07-18","code_links":[{"title":"twhui/LiteFlowNet3","url":"https://github.com/twhui/LiteFlowNet3"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52688,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"ContinualFlow + ft","metrics":{"Average End-Point Error":"4.52"},"paper_url":"http://arxiv.org/abs/1811.01602v1","paper_title":"Continual Occlusions and Optical Flow Estimation","paper_date":"2018-11-05","code_links":[],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52689,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"LiteFlowNet3-S","metrics":{"Average End-Point Error":"4.53"},"paper_url":"https://arxiv.org/abs/2007.09319v1","paper_title":"LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation","paper_date":"2020-07-18","code_links":[{"title":"twhui/LiteFlowNet3","url":"https://github.com/twhui/LiteFlowNet3"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52690,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"IRR-PWC","metrics":{"Average End-Point Error":"4.579"},"paper_url":"http://arxiv.org/abs/1904.05290v1","paper_title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","paper_date":"2019-04-10","code_links":[{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"visinf/irr","url":"https://github.com/visinf/irr"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52691,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"LiteFlowNet2-ft","metrics":{"Average End-Point Error":"4.69"},"paper_url":"https://arxiv.org/abs/1903.07414v3","paper_title":"A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization","paper_date":"2019-03-15","code_links":[{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"twhui/LiteFlowNet2","url":"https://github.com/twhui/LiteFlowNet2"},{"title":"rogerhcheng/LiteFlowNet2-TF2","url":"https://github.com/rogerhcheng/LiteFlowNet2-TF2"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52692,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"FDFlowNet-ft","metrics":{"Average End-Point Error":"5.11"},"paper_url":"https://arxiv.org/abs/2006.12263v1","paper_title":"FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network","paper_date":"2020-06-22","code_links":[],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52693,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"MR-Flow","metrics":{"Average End-Point Error":"5.38"},"paper_url":"http://arxiv.org/abs/1705.01352v1","paper_title":"Optical Flow in Mostly Rigid Scenes","paper_date":"2017-05-03","code_links":[],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52694,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"LiteFlowNet-ft","metrics":{"Average End-Point Error":"5.38"},"paper_url":"http://arxiv.org/abs/1805.07036v1","paper_title":"LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation","paper_date":"2018-05-18","code_links":[{"title":"open-mmlab/mmflow","url":"https://github.com/open-mmlab/mmflow"},{"title":"twhui/LiteFlowNet","url":"https://github.com/twhui/LiteFlowNet"},{"title":"sniklaus/pytorch-liteflownet","url":"https://github.com/sniklaus/pytorch-liteflownet"},{"title":"keeper121/liteflownet-tf2","url":"https://github.com/keeper121/liteflownet-tf2"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52695,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"UnrolledCost","metrics":{"Average End-Point Error":"5.8"},"paper_url":"https://arxiv.org/abs/2011.14814v3","paper_title":"Cost Function Unrolling in Unsupervised Optical Flow","paper_date":"2020-11-30","code_links":[{"title":"gallif/costfunctionunrolling","url":"https://github.com/gallif/costfunctionunrolling"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52696,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"FastFlowNet-ft","metrics":{"Average End-Point Error":"6.08"},"paper_url":"https://arxiv.org/abs/2103.04524v2","paper_title":"FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation","paper_date":"2021-03-08","code_links":[{"title":"ltkong218/FastFlowNet","url":"https://github.com/ltkong218/FastFlowNet"},{"title":"2023-MindSpore-1/ms-code-213","url":"https://github.com/2023-MindSpore-1/ms-code-213/tree/main/fastflow"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52697,"task":"Optical Flow Estimation","parent_task":null,"dataset":"Sintel-final","model_name":"Spynet","metrics":{"Average End-Point Error":"8.36"},"paper_url":"http://arxiv.org/abs/1611.00850v2","paper_title":"Optical Flow Estimation using a Spatial Pyramid Network","paper_date":"2016-11-03","code_links":[{"title":"philferriere/tfoptflow","url":"https://github.com/philferriere/tfoptflow"},{"title":"guanfuchen/video_obj","url":"https://github.com/guanfuchen/video_obj"},{"title":"sniklaus/pytorch-spynet","url":"https://github.com/sniklaus/pytorch-spynet"},{"title":"anuragranj/spynet","url":"https://github.com/anuragranj/spynet"},{"title":"GibranBenitez/IPN-hand","url":"https://github.com/GibranBenitez/IPN-hand"},{"title":"Yijunmaverick/FlowGrounded-VideoPrediction","url":"https://github.com/Yijunmaverick/FlowGrounded-VideoPrediction"},{"title":"Guillem96/spynet-pytorch","url":"https://github.com/Guillem96/spynet-pytorch"},{"title":"rickyHong/tfoptflow-repl","url":"https://github.com/rickyHong/tfoptflow-repl"}],"metrics_order":"[\"Average End-Point Error\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}