{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/raft-3d-scene-flow-using-rigid-motion","title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","arxiv_id":"2012.00726","date":"2020-12-01","proceeding":"CVPR 2021 1","authors":["Zachary Teed","Jia Deng"],"abstract":"We address the problem of scene flow: given a pair of stereo or RGB-D video frames, estimate pixelwise 3D motion. We introduce RAFT-3D, a new deep architecture for scene flow. RAFT-3D is based on the RAFT model developed for optical flow but iteratively updates a dense field of pixelwise SE3 motion instead of 2D motion. A key innovation of RAFT-3D is rigid-motion embeddings, which represent a soft grouping of pixels into rigid objects. Integral to rigid-motion embeddings is Dense-SE3, a differentiable layer that enforces geometric consistency of the embeddings. Experiments show that RAFT-3D achieves state-of-the-art performance. On FlyingThings3D, under the two-view evaluation, we improved the best published accuracy (d < 0.05) from 34.3% to 83.7%. On KITTI, we achieve an error of 5.77, outperforming the best published method (6.31), despite using no object instance supervision. Code is available at https://github.com/princeton-vl/RAFT-3D.","url_abs":"https://arxiv.org/abs/2012.00726v2","url_pdf":"https://arxiv.org/pdf/2012.00726v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"raft-3d-scene-flow-using-rigid-motion","repo_url":"https://github.com/princeton-vl/RAFT-3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"scene-flow-estimation","task_name":"Scene Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-flow-estimation-on-spring","task":"Scene Flow Estimation","dataset":"Spring","model":"RAFT-3D (K)","rank_in_archive_order":2,"of":6,"metrics":{"1px total":"37.262"},"uses_additional_data":false},{"leaderboard":"/sota/scene-flow-estimation-on-spring","task":"Scene Flow Estimation","dataset":"Spring","model":"RAFT-3D (F)","rank_in_archive_order":5,"of":6,"metrics":{"1px total":"78.822"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2012.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.00726"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/princeton-vl/RAFT-3D","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"63eb748c1573186d","entry":"fetch_optimizer","repo":"princeton-vl/RAFT-3D","repo_kind":"official","path":"scripts/train_things.py","file_url":"https://github.com/princeton-vl/RAFT-3D/blob/HEAD/scripts/train_things.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"63eb748c1573186d"}},{"code_sha256_prefix":"5573a1cb760609a7","entry":"loss_fn","repo":"princeton-vl/RAFT-3D","repo_kind":"official","path":"scripts/train_things.py","file_url":"https://github.com/princeton-vl/RAFT-3D/blob/HEAD/scripts/train_things.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5573a1cb760609a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}