Papers › Scalable Scene Flow from Point Clouds in the Real World

Scalable Scene Flow from Point Clouds in the Real World

1 Mar 2021arXiv:2103.01306archive 2025-07-28

Philipp Jund, Chris Sweeney, Nichola Abdo, Zhifeng Chen, Jonathon Shlens

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 ∼1,000× 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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

jabb0/fastflow3d mentioned on GitHubpytorchSyntology: not harvested report
kth-rpl/deflow mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
leolyj/dca-srsfe mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow... (arXiv:2203.16895; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
tudelft-iv/voteflow mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeFlow: Decoder of Scene Flow Network in Autonomous Driving (arXiv:2401.16122; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
kylevedder/zeroflow pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ZeroFlow: Scalable Scene Flow via Distillation (arXiv:2305.10424; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous VehiclesMotion EstimationScene Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Flow Estimation Argoverse 2 FastFlow3D EPE 3-Way 0.061960 #6 of 7 Archive leaderboard report
Scene Flow Estimation Argoverse 2 FastFlow3D EPE Background Static 0.004939 #6 of 7 Archive leaderboard report
Scene Flow Estimation Argoverse 2 FastFlow3D EPE Foreground Dynamic 0.156392 #6 of 7 Archive leaderboard report
Scene Flow Estimation Argoverse 2 FastFlow3D EPE Foreground Static 0.024549 #6 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections