{"url":"/dataset/mpi-sintel","name":"MPI Sintel","full_name":null,"description_markdown":"MPI (Max Planck Institute) Sintel is a dataset for optical flow evaluation that has 1064 synthesized stereo images and ground truth data for disparity. Sintel is derived from open-source 3D animated short film Sintel. The dataset has 23 different scenes. The stereo images are RGB while the disparity is grayscale. Both have resolution of 1024×436 pixels and 8-bit per channel.\r\n\r\nSource: [Fast Disparity Estimation using Dense Networks*](https://arxiv.org/abs/1805.07499)","description_withheld":null,"homepage":"http://sintel.is.tue.mpg.de/","introduced_date":"2012-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"A Naturalistic Open Source Movie for Optical Flow Evaluation","first_author":null,"url":"https://doi.org/10.1007/978-3-642-33783-3_44"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Stereo","url":"/datasets/modality/stereo"}],"tasks":[{"name":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Optical Flow Estimation","url":"/task/optical-flow-estimation","datasets_with_task":"/datasets/task/optical-flow-estimation"},{"name":"Style Transfer","url":"/task/style-transfer","datasets_with_task":"/datasets/task/style-transfer"},{"name":"Temporal View Synthesis","url":"/task/temporal-view-synthesis","datasets_with_task":"/datasets/task/temporal-view-synthesis"},{"name":"Intrinsic Image Decomposition","url":"/task/intrinsic-image-decomposition","datasets_with_task":"/datasets/task/intrinsic-image-decomposition"}],"languages":[],"variants":["Sintel-clean","Sintel-final","Sintel-final - unsupervised","Sintel Clean unsupervised","Sintel Final unsupervised","MPI Sintel"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Sintel.html","frameworks":["pytorch"]}],"num_papers_in_archive":198,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset_variant":"Sintel-clean","rows":29,"metrics":["Average End-Point Error"],"first_row_in_archive_order":{"model":"MEMFOF-L","paper":"/paper/memfof-high-resolution-training-for-memory","metrics":{"Average End-Point Error":"0.963"},"code_links":[{"title":"msu-video-group/memfof","url":"https://github.com/msu-video-group/memfof"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final","task":"Optical Flow Estimation","dataset_variant":"Sintel-final","rows":28,"metrics":["Average End-Point Error"],"first_row_in_archive_order":{"model":"MEMFOF-L","paper":"/paper/memfof-high-resolution-training-for-memory","metrics":{"Average End-Point Error":"1.907"},"code_links":[{"title":"msu-video-group/memfof","url":"https://github.com/msu-video-group/memfof"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean-2","task":"Optical Flow Estimation","dataset_variant":"Sintel Clean unsupervised","rows":5,"metrics":["Average End-Point Error"],"first_row_in_archive_order":{"model":"MDFlow","paper":"/paper/mdflow-unsupervised-optical-flow-learning-by","metrics":{"Average End-Point Error":"4.16"},"code_links":[{"title":"ltkong218/mdflow","url":"https://github.com/ltkong218/mdflow"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final-2","task":"Optical Flow Estimation","dataset_variant":"Sintel Final unsupervised","rows":5,"metrics":["Average End-Point Error"],"first_row_in_archive_order":{"model":"UpFlow","paper":"/paper/upflow-upsampling-pyramid-for-unsupervised","metrics":{"Average End-Point Error":"5.32"},"code_links":[{"title":"twhui/LiteFlowNet3","url":"https://github.com/twhui/LiteFlowNet3"},{"title":"coolbeam/UPFlow_pytorch","url":"https://github.com/coolbeam/UPFlow_pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-mpi-sintel","task":"Video Prediction","dataset_variant":"MPI Sintel","rows":1,"metrics":["LPIPS","PSNR","SSIM","ST-RRED"],"first_row_in_archive_order":{"model":"MCnet [villegas2017mcnet]","paper":"/paper/temporal-view-synthesis-of-dynamic-scenes","metrics":{"LPIPS":"0.223","PSNR":"24","SSIM":"0.7511","ST-RRED":"5.3"},"code_links":[{"title":"NagabhushanSN95/DeCOMPnet","url":"https://github.com/NagabhushanSN95/DeCOMPnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/memfof-high-resolution-training-for-memory","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","date":"2025-06-29","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":9,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dpflow-adaptive-optical-flow-estimation-with-1","title":"DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework","date":"2025-03-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/rapidflow-recurrent-adaptable-pyramids-with","title":"RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation","date":"2024-05-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/recurrent-partial-kernel-network-for","title":"Recurrent Partial Kernel Network for Efficient Optical Flow Estimation","date":"2024-02-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-raft-for-efficient-optical-flow","title":"Rethinking RAFT for Efficient Optical Flow","date":"2024-01-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/improved-cross-view-completion-pre-training","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","date":"2022-11-18","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/mdflow-unsupervised-optical-flow-learning-by","title":"MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation","date":"2022-11-11","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unifying-flow-stereo-and-depth-estimation","title":"Unifying Flow, Stereo and Depth Estimation","date":"2022-11-10","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/temporal-view-synthesis-of-dynamic-scenes","title":"Temporal View Synthesis of Dynamic Scenes through 3D Object Motion Estimation with Multi-Plane Images","date":"2022-08-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-equilibrium-optical-flow-estimation","title":"Deep Equilibrium Optical Flow Estimation","date":"2022-04-18","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/flowformer-a-transformer-architecture-for","title":"FlowFormer: A Transformer Architecture for Optical Flow","date":"2022-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/global-matching-with-overlapping-attention","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","date":"2022-03-21","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":7,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","date":"2021-07-30","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-estimate-hidden-motions-with","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","date":"2021-04-06","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fastflownet-a-lightweight-network-for-fast","title":"FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation","date":"2021-03-08","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/upflow-upsampling-pyramid-for-unsupervised","title":"UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning","date":"2020-12-01","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-optical-flow-using-cost-function","title":"Cost Function Unrolling in Unsupervised Optical Flow","date":"2020-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/liteflownet3-resolving-correspondence","title":"LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation","date":"2020-07-18","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/fdflownet-fast-optical-flow-estimation-using","title":"FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network","date":"2020-06-22","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/what-matters-in-unsupervised-optical-flow","title":"What Matters in Unsupervised Optical Flow","date":"2020-06-08","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":1,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-by-analogy-reliable-supervision-from","title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","date":"2020-03-29","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/raft-recurrent-all-pairs-field-transforms-for","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","date":"2020-03-26","rows_on_this_dataset":2,"code_links":17,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":66,"samples_ran":40,"samples_unverified":26,"pointer_only_for_licence":17,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/maskflownet-asymmetric-feature-matching-with","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","date":"2020-03-24","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scopeflow-dynamic-scene-scoping-for-optical","title":"ScopeFlow: Dynamic Scene Scoping for Optical Flow","date":"2020-02-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/volumetric-correspondence-networks-for","title":"Volumetric Correspondence Networks for Optical Flow","date":"2019-12-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/selflow-self-supervised-learning-of-optical","title":"SelFlow: Self-Supervised Learning of Optical Flow","date":"2019-04-19","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":0,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/iterative-residual-refinement-for-joint","title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","date":"2019-04-10","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-lightweight-optical-flow-cnn-revisiting","title":"A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization","date":"2019-03-15","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/continual-occlusions-and-optical-flow","title":"Continual Occlusions and Optical Flow Estimation","date":"2018-11-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/proflow-learning-to-predict-optical-flow","title":"ProFlow: Learning to Predict Optical Flow","date":"2018-06-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/liteflownet-a-lightweight-convolutional","title":"LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation","date":"2018-05-18","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/optical-flow-in-mostly-rigid-scenes","title":"Optical Flow in Mostly Rigid Scenes","date":"2017-05-03","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/flownet-20-evolution-of-optical-flow","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","date":"2016-12-06","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":2,"samples_unverified":19,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/optical-flow-estimation-using-a-spatial","title":"Optical Flow Estimation using a Spatial Pyramid Network","date":"2016-11-03","rows_on_this_dataset":2,"code_links":8,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":15,"samples_harvested":192,"samples_ran":74,"samples_unverified":118,"pointer_only_for_licence":24,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}