{"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/fast-neural-scene-flow","title":"Fast Neural Scene Flow","arxiv_id":"2304.09121","date":"2023-04-18","proceeding":"ICCV 2023 1","authors":["Xueqian Li","Jianqiao Zheng","Francesco Ferroni","Jhony Kaesemodel Pontes","Simon Lucey"],"abstract":"Neural Scene Flow Prior (NSFP) is of significant interest to the vision community due to its inherent robustness to out-of-distribution (OOD) effects and its ability to deal with dense lidar points. The approach utilizes a coordinate neural network to estimate scene flow at runtime, without any training. However, it is up to 100 times slower than current state-of-the-art learning methods. In other applications such as image, video, and radiance function reconstruction innovations in speeding up the runtime performance of coordinate networks have centered upon architectural changes. In this paper, we demonstrate that scene flow is different -- with the dominant computational bottleneck stemming from the loss function itself (i.e., Chamfer distance). Further, we rediscover the distance transform (DT) as an efficient, correspondence-free loss function that dramatically speeds up the runtime optimization. Our fast neural scene flow (FNSF) approach reports for the first time real-time performance comparable to learning methods, without any training or OOD bias on two of the largest open autonomous driving (AV) lidar datasets Waymo Open and Argoverse.","url_abs":"https://arxiv.org/abs/2304.09121v3","url_pdf":"https://arxiv.org/pdf/2304.09121v3.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":"fast-neural-scene-flow","repo_url":"https://github.com/lilac-lee/fastnsf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"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":"FastNSF","rank_in_archive_order":7,"of":7,"metrics":{"EPE 3-Way":"0.111820","EPE Background Static":"0.090712","EPE Foreground Dynamic":"0.163388","EPE Foreground Static":"0.081360"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-scene-flow-estimation-on-1","task":"Self-supervised Scene Flow Estimation","dataset":"Argoverse 2","model":"FastNSF","rank_in_archive_order":6,"of":6,"metrics":{"EPE 3-Way":"0.111820","EPE Background Static":"0.090712","EPE Foreground Dynamic":"0.115796","EPE Foreground Static":"0.031576"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.09121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09121"}},"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/lilac-lee/fastnsf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"b016aa0961874d5b","entry":"flow_to_rgb","repo":"lilac-lee/fastnsf","repo_kind":"official","path":"opt_linear.py","file_url":"https://github.com/lilac-lee/fastnsf/blob/HEAD/opt_linear.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b016aa0961874d5b"}},{"code_sha256_prefix":"4b45f1bdfa618295","entry":"make_colorwheel","repo":"lilac-lee/fastnsf","repo_kind":"official","path":"opt_linear.py","file_url":"https://github.com/lilac-lee/fastnsf/blob/HEAD/opt_linear.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b45f1bdfa618295"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}