paper-with-me

Scene Flow Estimation 벤치마크

Scene Flow Estimation on Argoverse 2

7개 결과 · ⬇ CSV · JSON

EPE 3-Way

0.03429 0.05368 0.07306 0.09244 0.1118 2021-03 2026-09 FastFlow3D — 0.06196 (2021-03-01) NSFP — 0.060606 (2021-11-01) FastNSF — 0.11182 (2023-04-18) ZeroFlow 5x XL — 0.049392 (2023-05-17) DeFlow — 0.034295 (2024-01-29) SeFlow — 0.04859 (2024-07-01) FastFlow3D — 0.06196 (2021-03-01) FastNSF — 0.11182 (2023-04-18)
RankModel EPE 3-WayEPE Foreground DynamicEPE Foreground StaticEPE Background Static Extra Training Data PaperCodeYear
1 DeFlow 0.0342950.0732310.0250930.004561 DeFlow: Decoder of Scene Flow Network in Autonomous Driving kth-rpl/dynamicmap_benchmark · kth-rpl/deflow · kth-rpl/seflow · +1 2024
2 TrackFlow 0.0473160.1029750.0365440.002428
3 SeFlow 0.0485900.1213750.0184040.005990 SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving kth-rpl/deflow · kth-rpl/seflow 2024
4 ZeroFlow 5x XL 0.0493920.1176880.0174060.013082 ZeroFlow: Scalable Scene Flow via Distillation kylevedder/zeroflow 2023
5 NSFP 0.0606060.1157960.0315760.034445 Neural Scene Flow Prior lilac-lee/neural_scene_flow_prior 2021
6 FastFlow3D 0.0619600.1563920.0245490.004939 Scalable Scene Flow from Point Clouds in the Real World kth-rpl/deflow · leolyj/dca-srsfe · jabb0/fastflow3d · +2 2021
7 FastNSF 0.1118200.1633880.0813600.090712 Fast Neural Scene Flow lilac-lee/fastnsf 2023
1–7 / 7 페이지당 10 20 50 100