{"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/zeroflow-fast-zero-label-scene-flow-via","title":"ZeroFlow: Scalable Scene Flow via Distillation","arxiv_id":"2305.10424","date":"2023-05-17","proceeding":null,"authors":["Kyle Vedder","Neehar Peri","Nathaniel Chodosh","Ishan Khatri","Eric Eaton","Dinesh Jayaraman","Yang Liu","Deva Ramanan","James Hays"],"abstract":"Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to process full-size point clouds, making them unusable as computer vision primitives for real-time applications such as open world object detection. Feedforward methods are considerably faster, running on the order of tens to hundreds of milliseconds for full-size point clouds, but require expensive human supervision. To address both limitations, we propose Scene Flow via Distillation, a simple, scalable distillation framework that uses a label-free optimization method to produce pseudo-labels to supervise a feedforward model. Our instantiation of this framework, ZeroFlow, achieves state-of-the-art performance on the Argoverse 2 Self-Supervised Scene Flow Challenge while using zero human labels by simply training on large-scale, diverse unlabeled data. At test-time, ZeroFlow is over 1000x faster than label-free state-of-the-art optimization-based methods on full-size point clouds (34 FPS vs 0.028 FPS) and over 1000x cheaper to train on unlabeled data compared to the cost of human annotation (\\$394 vs ~\\$750,000). To facilitate further research, we release our code, trained model weights, and high quality pseudo-labels for the Argoverse 2 and Waymo Open datasets at https://vedder.io/zeroflow.html","url_abs":"https://arxiv.org/abs/2305.10424v8","url_pdf":"https://arxiv.org/pdf/2305.10424v8.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":"zeroflow-fast-zero-label-scene-flow-via","repo_url":"https://github.com/kylevedder/zeroflow","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"scene-flow-estimation","task_name":"Scene Flow Estimation"},{"task_slug":"self-supervised-scene-flow-estimation","task_name":"Self-supervised Scene Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-flow-estimation-on-argoverse-2","task":"Scene Flow Estimation","dataset":"Argoverse 2","model":"ZeroFlow 5x XL","rank_in_archive_order":4,"of":7,"metrics":{"EPE 3-Way":"0.049392","EPE Background Static":"0.013082","EPE Foreground Dynamic":"0.117688","EPE Foreground Static":"0.017406"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-scene-flow-estimation-on-1","task":"Self-supervised Scene Flow Estimation","dataset":"Argoverse 2","model":"ZeroFlow 5x XL","rank_in_archive_order":2,"of":6,"metrics":{"EPE 3-Way":"0.049392","EPE Background Static":"0.013082","EPE Foreground Dynamic":"0.117688","EPE Foreground Static":"0.017406"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-scene-flow-estimation-on-1","task":"Self-supervised Scene Flow Estimation","dataset":"Argoverse 2","model":"ZeroFlow","rank_in_archive_order":5,"of":6,"metrics":{"EPE 3-Way":"0.0814","EPE Foreground Dynamic":"0.2109","EPE Foreground Static":"0.0254"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.10424","atlas_url":"https://app.syntology.ai/?focus=2305.10424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10424"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kylevedder/zeroflow","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":"2d7c18a592896780","entry":"get_checkpoint_path","repo":"kylevedder/zeroflow","repo_kind":"official","path":"train_pl.py","file_url":"https://github.com/kylevedder/zeroflow/blob/HEAD/train_pl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d7c18a592896780"}},{"code_sha256_prefix":"9122e8700aed2673","entry":"get_max_sequence_length","repo":"kylevedder/zeroflow","repo_kind":"official","path":"configs/fastflow3d/argo/nsfp_distilatation.py","file_url":"https://github.com/kylevedder/zeroflow/blob/HEAD/configs/fastflow3d/argo/nsfp_distilatation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9122e8700aed2673"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}