{"url":"/sota/scene-flow-estimation-on-spring","task":{"name":"Scene Flow Estimation","url":"/task/scene-flow-estimation","note":null},"dataset":{"name":"Spring","url":"/dataset/spring"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Optical flow is a two-dimensional motion field in the image plane. It is the projection of the three-dimensional motion of the world. If the world is completely non-rigid, the motions of the points in the scene may all be indepen- dent of each other. One representation of the scene motion is therefore a dense **three-dimensional vector field** defined for every point on every surface in the scene. By analogy with optical flow, we refer to this three-dimensional motion field as **scene flow**.\r\n\r\nSource: Vedula, Sundar, et al. \"Three-dimensional scene flow.\" IEEE transactions on pattern analysis and machine intelligence 27.3 (2005): 475-480. [pdf](https://ieeexplore.ieee.org/document/1388274)","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":["1px total"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"1px total":null}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"M-FUSE (F)","metrics":{"1px total":"34.896"},"uses_additional_data":false,"paper_date":"2022-07-12","paper":"/paper/m-fuse-multi-frame-fusion-for-scene-flow","paper_url":"https://arxiv.org/abs/2207.05704v2","paper_title":"M-FUSE: Multi-frame Fusion for Scene Flow Estimation","code":"https://github.com/cv-stuttgart/m-fuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"RAFT-3D (K)","metrics":{"1px total":"37.262"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/raft-3d-scene-flow-using-rigid-motion","paper_url":"https://arxiv.org/abs/2012.00726v2","paper_title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","code":"https://github.com/princeton-vl/RAFT-3D","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CamLiFlow (F)","metrics":{"1px total":"50.083"},"uses_additional_data":false,"paper_date":"2021-11-20","paper":"/paper/camliflow-bidirectional-camera-lidar-fusion","paper_url":"https://arxiv.org/abs/2111.10502v4","paper_title":"CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation","code":"https://github.com/mcg-nju/camliflow","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"M-FUSE (K)","metrics":{"1px total":"62.490"},"uses_additional_data":false,"paper_date":"2022-07-12","paper":"/paper/m-fuse-multi-frame-fusion-for-scene-flow","paper_url":"https://arxiv.org/abs/2207.05704v2","paper_title":"M-FUSE: Multi-frame Fusion for Scene Flow Estimation","code":"https://github.com/cv-stuttgart/m-fuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"RAFT-3D (F)","metrics":{"1px total":"78.822"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/raft-3d-scene-flow-using-rigid-motion","paper_url":"https://arxiv.org/abs/2012.00726v2","paper_title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","code":"https://github.com/princeton-vl/RAFT-3D","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CamLiFlow (K)","metrics":{"1px total":"85.310"},"uses_additional_data":false,"paper_date":"2021-11-20","paper":"/paper/camliflow-bidirectional-camera-lidar-fusion","paper_url":"https://arxiv.org/abs/2111.10502v4","paper_title":"CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation","code":"https://github.com/mcg-nju/camliflow","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":1,"n_samples":2,"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":2,"n_unverified":2,"n_samples":4,"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"}}}