{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/scalable-scene-flow-from-point-clouds-in-the","title":"Scalable Scene Flow from Point Clouds in the Real World","arxiv_id":"2103.01306","date":"2021-03-01","proceeding":null,"authors":["Philipp Jund","Chris Sweeney","Nichola Abdo","Zhifeng Chen","Jonathon Shlens"],"abstract":"Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ 3D point cloud data from consecutive LiDAR scans, although such approaches have been limited by the small size of real-world, annotated LiDAR data. In this work, we introduce a new large-scale dataset for scene flow estimation derived from corresponding tracked 3D objects, which is $\\sim$1,000$\\times$ larger than previous real-world datasets in terms of the number of annotated frames. We demonstrate how previous works were bounded based on the amount of real LiDAR data available, suggesting that larger datasets are required to achieve state-of-the-art predictive performance. Furthermore, we show how previous heuristics for operating on point clouds such as down-sampling heavily degrade performance, motivating a new class of models that are tractable on the full point cloud. To address this issue, we introduce the FastFlow3D architecture which provides real time inference on the full point cloud. Additionally, we design human-interpretable metrics that better capture real world aspects by accounting for ego-motion and providing breakdowns per object type. We hope that this dataset may provide new opportunities for developing real world scene flow systems.","url_abs":"https://arxiv.org/abs/2103.01306v5","url_pdf":"https://arxiv.org/pdf/2103.01306v5.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":"scalable-scene-flow-from-point-clouds-in-the","repo_url":"https://github.com/jabb0/fastflow3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"scalable-scene-flow-from-point-clouds-in-the","repo_url":"https://github.com/kth-rpl/deflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"scalable-scene-flow-from-point-clouds-in-the","repo_url":"https://github.com/leolyj/dca-srsfe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"scalable-scene-flow-from-point-clouds-in-the","repo_url":"https://github.com/tudelft-iv/voteflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"scalable-scene-flow-from-point-clouds-in-the","repo_url":"https://github.com/kylevedder/zeroflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"motion-estimation","task_name":"Motion Estimation"},{"task_slug":"scene-flow-estimation","task_name":"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":"FastFlow3D","rank_in_archive_order":6,"of":7,"metrics":{"EPE 3-Way":"0.061960","EPE Background Static":"0.004939","EPE Foreground Dynamic":"0.156392","EPE Foreground Static":"0.024549"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.01306","atlas_url":"https://app.syntology.ai/?focus=2103.01306","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2103.01306"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.01306\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.01306"},"call":"get_concepts_for_paper(arxiv_id=\"2103.01306\")"}],"by_repo":[{"repo":"jabb0/fastflow3d","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kth-rpl/deflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"leolyj/dca-srsfe","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.16895"],"harvested_for_calls":[{"arxiv_id":"2203.16895","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.16895"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.16895\")"}]},{"repo":"tudelft-iv/voteflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.16122"],"harvested_for_calls":[{"arxiv_id":"2401.16122","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.16122"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.16122\")"}]},{"repo":"kylevedder/zeroflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.10424"],"harvested_for_calls":[{"arxiv_id":"2305.10424","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.10424"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.10424\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ed98f9cde85cb7f685d655c0440086adc5fd5c0f00dc9ef8bc745c2df61bd997","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}