Scene Flow Estimation On Argoverse 2
Metriken
EPE 3-Way
EPE Background Static
EPE Foreground Dynamic
EPE Foreground Static
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | |||||
|---|---|---|---|---|---|
| FastNSF | 0.111820 | 0.090712 | 0.163388 | 0.081360 | Fast Neural Scene Flow |
| FastFlow3D | 0.061960 | 0.004939 | 0.156392 | 0.024549 | Scalable Scene Flow from Point Clouds in the Real World |
| NSFP | 0.060606 | 0.034445 | 0.115796 | 0.031576 | Neural Scene Flow Prior |
| ZeroFlow 5x XL | 0.049392 | 0.013082 | 0.117688 | 0.017406 | ZeroFlow: Scalable Scene Flow via Distillation |
| SeFlow | 0.048590 | 0.005990 | 0.121375 | 0.018404 | SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving |
| TrackFlow | 0.047316 | 0.002428 | 0.102975 | 0.036544 | - |
| DeFlow | 0.034295 | 0.004561 | 0.073231 | 0.025093 | DeFlow: Decoder of Scene Flow Network in Autonomous Driving |
0 of 7 row(s) selected.