3D Object Detection on Argoverse 2 (val)
51.2mAPMambaFusion
Evaluation Results
| Method | Links | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MambaFusionModality=Camera-LiDAR Fusion2026.02 | 51.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 41.5 | 0.35 | 0.255 | 0.488 | — | — | |
| MV2DFusionModality=Camera-LiDAR Fusion2026.02 | 48.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 39.5 | 0.368 | 0.267 | 0.51 | — | — | |
| GraphBEV++ (LSS)Venue=-2026.06 | 46.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GraphBEVVenue=ECCV’242026.06 | 46.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BEVFusion†Venue=ICRA’232026.06 | 43.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UniMamba2025.03 | 42 | 78.9 | 47.9 | 74.3 | 51.8 | 46.8 | 67.8 | 76.9 | 55.8 | 51.7 | 62.8 | 52.2 | 30.2 | 44.6 | 24.6 | 28.1 | 59.4 | 32.2 | 23.2 | 6.7 | 41.5 | 48.5 | 0 | 26.4 | 8.1 | 36.4 | 13.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UniMambaVenue=CVPR’252026.06 | 42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ours2025.07 | 41.7 | 76.2 | 49 | 58.5 | 78.1 | 56.8 | 49.8 | 65.1 | 31.2 | 48.5 | 31 | 26.9 | 68.1 | 65.8 | 43.7 | 50.3 | 46 | 62.5 | 27.5 | 45.8 | 25 | 33.8 | — | 18.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GeoFormerVenue=ICCV’252026.06 | 41.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PGDCVenue=CVPR’262026.06 | 41.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LION-Mamba2025.03 | 41.5 | 75.1 | 43.6 | 73.9 | 53.9 | 45.1 | 66.4 | 74.7 | 61.3 | 48.7 | 65.1 | 56.2 | 21.7 | 42.7 | 19 | 25.3 | 58.4 | 28.9 | 23.6 | 8.3 | 49.5 | 47.3 | 0 | 31.4 | 8.7 | 37.6 | 11.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LION-Mamba2024.07 | 41.5 | 75.1 | 43.6 | 73.9 | 53.9 | 45.1 | 66.4 | 74.7 | 61.3 | 48.7 | 65.1 | 56.2 | 21.7 | 42.7 | 19 | 25.3 | 58.4 | 28.9 | 23.6 | 8.3 | 49.5 | 47.3 | 0 | 31.4 | 8.7 | 37.6 | 11.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LION-MambaVenue=NeurPS’242026.06 | 41.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LION-RWKV2024.07 | 41.1 | 76.3 | 44.6 | 74 | 52.1 | 46 | 68.1 | 75.8 | 55.8 | 49.4 | 62.8 | 55.3 | 27.1 | 42.9 | 23.2 | 25.9 | 60.1 | 30.9 | 22.2 | 9.3 | 36.5 | 55.3 | 0 | 27.8 | 7.1 | 37.6 | 11.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GraphBEV2025.07 | 41.1 | 75.2 | 48 | 57.6 | 77.3 | 55.7 | 48.8 | 64.2 | 30.1 | 47.7 | 29.5 | 25.8 | 68.5 | 64.7 | 44.2 | 48.2 | 44.5 | 62.7 | 26.2 | 44.2 | 23.8 | 32.6 | — | 17.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| M3Net2025.07 | 40.9 | 74.9 | 47.8 | 57.4 | 77.1 | 55.3 | 48.5 | 63.9 | 29.9 | 47.5 | 28.2 | 25.4 | 67 | 64.2 | 40.2 | 46.8 | 43.8 | 59.5 | 24 | 41.5 | 21.8 | 30.5 | — | 15.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| M3NetVenue=Arxiv’232026.06 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LION-RetNet2024.07 | 40.7 | 74.7 | 41 | 72.7 | 47.5 | 44.2 | 66.9 | 77 | 57.1 | 48.3 | 63.7 | 55.1 | 27 | 42.5 | 19.9 | 25.2 | 57.9 | 29.7 | 22 | 6.9 | 39.3 | 47.3 | 0 | 28.8 | 12.8 | 37.7 | 12.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LION2025.07 | 40.7 | 74.7 | 47.5 | 57.1 | 77 | 55.1 | 48.3 | 63.7 | 29.7 | 47.3 | 27 | 25.2 | 66.9 | 63.7 | 37.7 | 44.2 | 42.5 | 57.9 | 22 | 39.3 | 19.9 | 28.8 | — | 12.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSHNetbasePerception range=200m, Training strategy=36 epochs without CBGS2025.06 | 40.2 | 77.4 | 48.3 | 72.9 | 50 | 47.2 | 63.4 | 69.9 | 56.1 | 43.8 | 62.5 | 53.7 | 31.8 | 44.8 | — | 28.9 | 56.6 | 32 | 23 | 8.7 | 34.5 | 41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSHNet2025.07 | 40.2 | 75.1 | 47.1 | 50.3 | 76.2 | 54.9 | 46 | 62.1 | 28.5 | 45.8 | 29.1 | 25.4 | 64.8 | 64.1 | 43 | 48.9 | 44.5 | 61.3 | 26 | 44.1 | 23.6 | 32.5 | — | 17.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSHNetVenue=CVPR’252026.06 | 40.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SparseFusionModality=Camera-LiDAR Fusion2026.02 | 39.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31 | 0.449 | 0.308 | 0.677 | — | — | |
| SAFDNet2025.03 | 39.7 | 78.5 | 49.4 | 70.7 | 51.5 | 44.7 | 65.7 | 72.3 | 54.3 | 49.7 | 60.8 | 50 | 31.3 | 44.9 | 23.6 | 24.7 | 55.4 | 31.4 | 22.1 | 7.1 | 31.1 | 42.7 | 0 | 26.1 | 1.4 | 30.2 | 11.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAFDNet2024.07 | 39.7 | 78.5 | 49.4 | 70.7 | 51.5 | 44.7 | 65.7 | 72.3 | 54.3 | 49.7 | 60.8 | 50 | 31.3 | 44.9 | 23.6 | 24.7 | 55.4 | 31.4 | 22.1 | 7.1 | 31.1 | 42.7 | 0 | 26.1 | 1.4 | 30.2 | 11.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAFDNetModality=LiDAR-only2026.02 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAFDNetFPS=10.8, Params=6.11M, Speedup=1.0×2025.09 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAFDNet2025.07 | 39.7 | 74.3 | 46.8 | 49.5 | 75.1 | 53 | 45.1 | 60.3 | 27.8 | 43.5 | 28.5 | 25 | 63.2 | 62.9 | 41.9 | 47.8 | 43.1 | 60.1 | 24.9 | 43.2 | 22.5 | 31.8 | — | 16.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DualViewMapDetBackbone=VoVNet-99, Input image resolution=640x960, Evaluation range=50 meters, Training sampling frequency=strict 2 Hz subsampling2026.04 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.1 | 0.622 | 0.279 | 0.527 | — | — | |
| SAFDNetVenue=CVPR’242026.06 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BEVFusionModality=Camera-LiDAR Fusion2026.02 | 38.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.1 | 0.45 | 0.336 | 0.643 | — | — | |
| SAFDNetPerception range=200m, Codebase=OpenPCDet, Training strategy=36 epochs without CBGS2025.06 | 38.7 | 77.7 | 47.3 | 69.4 | 49.8 | 45.9 | 62.2 | 69.5 | 52.5 | 45.4 | 59.5 | 48.5 | 29.6 | 43.3 | — | 25.7 | 54.2 | 31.2 | 20.5 | 9.3 | 36 | 48.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PointSlice-AFPS=11.9, Params=4.05M, Speedup=1.1×2025.09 | 38.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| BEVFusion2025.07 | 38.1 | 72.1 | 45.3 | 48 | 73.5 | 51.2 | 43.5 | 58.9 | 25.8 | 42.1 | 27.3 | 23.9 | 61.1 | 61.3 | 40.1 | 45.2 | 42 | 58.2 | 23.5 | 41.9 | 21 | 30.2 | — | 14.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Sparse4Dv3Backbone=VoVNet-99, Input image resolution=640x960, Evaluation range=50 meters, Training sampling frequency=10 Hz, Baseline source=Trained by authors with provided code2026.04 | 38.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 29.4 | 0.706 | 0.314 | 0.666 | — | — | |
| FSDv22025.03 | 37.6 | 77 | 47.6 | 70.5 | 43.6 | 41.5 | 53.9 | 58.5 | 56.8 | 39 | 60.7 | 49.4 | 28.4 | 41.9 | 24 | 30.2 | 44.9 | 33.4 | 16.6 | 7.3 | 32.5 | 45.9 | 1 | 12.6 | 17.1 | 26.3 | 17.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv2Fully sparse detector=true2023.08 | 37.6 | 77 | 47.6 | 70.5 | 43.6 | 41.5 | 53.9 | 58.5 | 56.8 | 39 | 60.7 | 49.4 | 28.4 | 41.9 | 24 | 30.2 | 44.9 | 33.4 | 16.6 | 7.3 | 32.5 | 45.9 | 1 | 12.6 | 17.1 | 26.3 | 17.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv22024.07 | 37.6 | 77 | 47.6 | 70.5 | 43.6 | 41.5 | 53.9 | 58.5 | 56.8 | 39 | 60.7 | 49.4 | 28.4 | 41.9 | 24 | 30.2 | 44.9 | 33.4 | 16.6 | 7.3 | 32.5 | 45.9 | 1 | 12.6 | 17.1 | 26.3 | 17.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv2Perception range=200m, Training strategy=36 epochs without CBGS2025.06 | 37.6 | 77 | 47.6 | 70.5 | 43.6 | 41.5 | 53.9 | 58.5 | 56.8 | 39 | 60.7 | 49.4 | 28.4 | 41.9 | — | 30.2 | 44.9 | 33.4 | 16.6 | 7.3 | 32.5 | 45.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv2Modality=LiDAR-only2026.02 | 37.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.2 | 0.377 | 0.282 | 0.6 | — | — | |
| Sparse4Dv3Backbone=VoVNet-99, Input image resolution=640x960, Evaluation range=50 meters, Training sampling frequency=strict 2 Hz subsampling, Baseline source=Trained by authors with provided code2026.04 | 37.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.8 | 0.694 | 0.298 | 0.547 | — | — | |
| FSDv2Venue=TPAMI’242026.06 | 37.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HEDNet2025.03 | 37.1 | 78.2 | 47.7 | 67.6 | 46.4 | 45.9 | 56.9 | 67 | 48.7 | 46.5 | 58.2 | 47.5 | 23.3 | 40.9 | 21.6 | 27.5 | 46.8 | 27.9 | 20.6 | 6.9 | 27.2 | 38.7 | 0 | 30.7 | 9.5 | 28.5 | 8.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HEDNet2024.07 | 37.1 | 78.2 | 47.7 | 67.6 | 46.4 | 45.9 | 56.9 | 67 | 48.7 | 46.5 | 58.2 | 47.5 | 23.3 | 40.9 | 21.6 | 27.5 | 46.8 | 27.9 | 20.6 | 6.9 | 27.2 | 38.7 | 0 | 30.7 | 0.5 | 10.9 | 4.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HEDNetPerception range=200m2025.06 | 37.1 | 78.2 | 47.7 | 67.6 | 46.4 | 45.9 | 56.9 | 67 | 48.7 | 46.5 | 58.2 | 47.5 | 23.3 | 40.9 | — | 27.5 | 46.8 | 27.9 | 20.6 | 6.9 | 27.2 | 38.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HEDNetVenue=NeurPS’232026.06 | 37.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Far3DBackbone=VoVNet-99, Input image resolution=640x960, Evaluation range=50 meters, Training sampling frequency=10 Hz2026.04 | 36.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.1 | 0.73 | 0.3 | 0.531 | — | — | |
| CMTModality=Camera-LiDAR Fusion2026.02 | 36.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 27.8 | 0.585 | 0.34 | 0.614 | — | — | |
| FSDv2Fully sparse detector=true, CopyPaste augmentation=false2023.08 | 36 | 76.6 | 46 | 69.8 | 39.9 | 39.5 | 52.8 | 57.6 | 55.4 | 35.4 | 57.8 | 49.2 | 24.7 | 37.2 | 22.5 | 27.4 | 41.3 | 32.1 | 16.5 | 6.4 | 36.1 | 44.6 | 0.9 | 12.1 | 14.7 | 23.3 | 16 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSFModality=Camera-LiDAR Fusion2026.02 | 33.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 25.5 | 0.442 | 0.328 | 0.668 | — | — | |
| VoxelNeXtPerception range=200m, Codebase=OpenPCDet, Training strategy=36 epochs without CBGS2025.06 | 33.1 | 74.8 | 43.2 | 65.5 | 36.3 | 43.1 | 58.7 | 67.5 | 29.4 | 43.3 | 54 | 45.4 | 21.7 | 41.8 | — | 23.8 | 51.2 | 28.3 | 17.9 | 6.3 | 13.1 | 29.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Far3DBackbone=ViT-L, Modality=Camera, Image/Voxel Size=1536 x 15362023.08 | 31.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.9 | 0.732 | 0.303 | 0.459 | — | — | |
| Far3DModality=Camera-only2026.02 | 31.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.9 | 0.732 | 0.303 | 0.459 | — | — | |
| RayMambabaseline=VoxelNeXt2026.04 | 31.2 | 73.7 | 39.8 | 64.6 | 40.1 | 40.5 | 56.5 | 69.3 | 46 | 34.5 | 47.3 | 40.9 | 20.6 | 26.4 | — | 19.6 | 45.5 | 21.5 | 16.6 | 6.1 | 15.7 | 35 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXt2025.03 | 30.7 | 72.7 | 38.8 | 63.2 | 40.2 | 40.1 | 53.9 | 64.9 | 44.7 | 39.4 | 42.4 | 40.6 | 20.1 | 25.2 | 16.9 | 19.9 | 44.9 | 20.9 | 14.9 | 6.8 | 15.7 | 32.4 | 0 | 14.4 | 0.1 | 17.4 | 6.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXtFully sparse detector=true, CopyPaste augmentation=false2023.08 | 30.7 | 72.7 | 38.8 | 63.2 | 40.2 | 40.1 | 53.9 | 64.9 | 44.7 | 39.4 | 42.4 | 40.6 | 20.1 | 25.2 | 16.9 | 19.9 | 44.9 | 20.9 | 14.9 | 6.8 | 15.7 | 32.4 | 0 | 14.4 | 0.1 | 17.4 | 6.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXtModality=Lidar, Image/Voxel Size=(0.1, 0.1, 0.2)2023.08 | 30.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 22.5 | 0.431 | 0.291 | 1.157 | — | — | |
| VoxelNeXt2024.07 | 30.7 | 72.7 | 38.8 | 63.2 | 40.2 | 40.1 | 53.9 | 64.9 | 44.7 | 39.4 | 42.4 | 40.6 | 20.1 | 25.2 | 16.9 | 19.9 | 44.9 | 20.9 | 14.9 | 6.8 | 15.7 | 32.4 | 0 | 14.4 | 0.1 | 17.4 | 6.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXtModality=LiDAR-only2026.02 | 30.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXt2025.07 | 30.7 | 65.2 | 40.1 | 42.5 | 64.9 | 46.8 | 40.1 | 52.3 | 22.5 | 38 | 24.1 | 21.3 | 56.2 | 56 | 36.3 | 39.9 | 38.1 | 54.8 | 20.2 | 38 | 18.2 | 27.1 | — | 11.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXt2026.04 | 30.3 | 72.1 | 38.5 | 63.2 | 37.5 | 40.5 | 52.8 | 64.9 | 44.4 | 35.3 | 44.8 | 39.3 | 21.5 | 27.5 | — | 17.4 | 45.4 | 21.2 | 16.4 | 7.1 | 12.3 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxelNeXt*Venue=CVPR’232026.06 | 30 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDModality=Lidar, Image/Voxel Size=(0.2, 0.2, 0.2)2023.08 | 29.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.3 | 0.468 | 0.299 | 0.74 | — | — | |
| FSDv12025.03 | 28.2 | 68.1 | 40.9 | 59 | 29 | 38.5 | 41.8 | 42.6 | 39.7 | 26.2 | 49 | 38.6 | 20.4 | 30.5 | 21.1 | 14.8 | 41.2 | 26.9 | 11.9 | 5.9 | 13.8 | 33.4 | 0 | 9.5 | 7.1 | 14 | 9.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv1Fully sparse detector=true, CopyPaste augmentation=false2023.08 | 28.2 | 68.1 | 40.9 | 59 | 29 | 38.5 | 41.8 | 42.6 | 39.7 | 26.2 | 49 | 38.6 | 20.4 | 30.5 | 21.1 | 14.8 | 41.2 | 26.9 | 11.9 | 5.9 | 13.8 | 33.4 | 0 | 9.5 | 7.1 | 14 | 9.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv12024.07 | 28.2 | 68.1 | 40.9 | 59 | 29 | 38.5 | 41.8 | 42.6 | 39.7 | 26.2 | 49 | 38.6 | 20.4 | 30.5 | 21.1 | 14.8 | 41.2 | 26.9 | 11.9 | 5.9 | 13.8 | 33.4 | 0 | 9.5 | 7.1 | 14 | 9.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDv1Perception range=200m, Training strategy=36 epochs without CBGS2025.06 | 28.2 | 68.1 | 40.9 | 59 | 29 | 38.5 | 41.8 | 42.6 | 39.7 | 26.2 | 49 | 38.6 | 20.4 | 30.5 | — | 14.8 | 41.2 | 26.9 | 11.9 | 5.9 | 13.8 | 33.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSDModality=LiDAR-only2026.02 | 28.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 22.7 | 0.414 | 0.306 | 0.645 | — | — | |
| FSD2026.04 | 28.2 | 68.1 | 40.9 | 59 | 29 | 38.5 | 41.8 | 42.6 | 39.7 | 26.2 | 49 | 38.6 | 20.4 | 30.5 | — | 14.8 | 41.2 | 26.9 | 11.9 | 5.9 | 13.8 | 33.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSD*Venue=NeurPS’222026.06 | 28.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CenterPointModality=Lidar, Image/Voxel Size=(0.2, 0.2, 0.2)2023.08 | 27.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 21 | 0.548 | 0.362 | 0.781 | — | — | |
| CAM3DNetBackbone=V2-99, Image Size=640 × 960, Input=C2026.04 | 26.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 19.3 | 0.812 | 0.275 | 0.556 | — | — | |
| DualViewDistillBackbone=V2-99, Image Size=640 × 960, Input=C2026.04 | 26.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 19.8 | 0.734 | 0.299 | 0.573 | — | — | |
| DualViewMapDetBackbone=VoVNet-99, Input image resolution=640x960, Training subsampling strategy=strict 2 Hz subsampling, Evaluation range=150 meters2026.04 | 26.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 20.2 | 0.667 | 0.291 | 0.515 | — | — | |
| SemLT3DBackbone=VoV-992026.04 | 25.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 19.4 | 0.792 | 0.308 | 0.48 | — | — | |
| Sparse4Dv3Backbone=VoVNet-99, Input image resolution=640x960, Training subsampling strategy=10 Hz subsequences, Evaluation range=150 meters, Implementation source=Baselines trained by authors2026.04 | 24.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.6 | 0.692 | 0.302 | 0.558 | — | — | |
| Far3DBackbone=VoV-99, Modality=Camera, Image/Voxel Size=960 x 6402023.08 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.1 | 0.796 | 0.304 | 0.538 | — | — | |
| Far3DBackbone=V2-99, Image Size=640 × 960, Input=C2026.04 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.1 | 0.796 | 0.304 | 0.538 | — | — | |
| Far3DBackbone=VoV-992026.04 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.1 | 0.796 | 0.304 | 0.538 | — | — | |
| Far3DBackbone=VoVNet-99, Input image resolution=640x960, Training subsampling strategy=10 Hz subsequences, Evaluation range=150 meters2026.04 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.1 | 0.796 | 0.304 | 0.538 | — | — | |
| Sparse4Dv3Backbone=VoVNet-99, Input image resolution=640x960, Training subsampling strategy=strict 2 Hz subsampling, Evaluation range=150 meters, Implementation source=Baselines trained by authors2026.04 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.2 | 0.726 | 0.307 | 0.548 | — | — | |
| Far3DVenue=AAAI’242026.06 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RayDNBackbone=V2-99, Image Size=900x6402024.02 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 16.1 | 0.825 | 0.325 | 0.629 | — | — | |
| RayDNBackbone=VoVNet-99, Input image resolution=640x960, Training subsampling strategy=10 Hz subsequences, Evaluation range=150 meters2026.04 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 16.1 | 0.825 | 0.325 | 0.629 | — | — | |
| CenterPoint2025.03 | 22 | 67.6 | 38.9 | 46.5 | 16.9 | 37.4 | 40.1 | 32.2 | 28.6 | 27.4 | 33.4 | 24.5 | 8.7 | 25.8 | 22.1 | 22.6 | 29.5 | 22.4 | 6.3 | 3.9 | 0.5 | 20.1 | 0 | 3.9 | 0.5 | 10.9 | 4.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CenterPointImplementation=re-implemented by authors2023.08 | 22 | 67.6 | 38.9 | 46.5 | 16.9 | 37.4 | 40.1 | 32.2 | 28.6 | 27.4 | 33.4 | 24.5 | 8.7 | 25.8 | 22.1 | 22.6 | 29.5 | 22.4 | 6.3 | 3.9 | 0.5 | 20.1 | 0 | 3.9 | 0.5 | 10.9 | 4.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CenterPoint2024.07 | 22 | 67.6 | 38.9 | 46.5 | 16.9 | 37.4 | 9.5 | 28.5 | 8.7 | 40.1 | 32.2 | 28.6 | 27.4 | 33.4 | 3.9 | 24.5 | 8.7 | 25.8 | 22.6 | 29.5 | 22.4 | 6.3 | 0 | 20.1 | 22.1 | 0 | 3.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CenterPointPerception range=200m2025.06 | 22 | 67.6 | 38.9 | 46.5 | 16.9 | 37.4 | 40.1 | 32.2 | 28.6 | 27.4 | 33.4 | 24.5 | 8.7 | 25.8 | — | 22.6 | 29.5 | 22.4 | 6.3 | 3.9 | 0.5 | 20.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CenterPointModality=LiDAR-only2026.02 | 22 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.6 | — | — | — | — | — | |
| CenterPoint2026.04 | 22 | 67.6 | 38.9 | 46.5 | 16.9 | 37.4 | 40.1 | 32.2 | 28.6 | 27.4 | 33.4 | 24.5 | 8.7 | 25.8 | — | 22.6 | 29.5 | 22.4 | 6.3 | 3.9 | 0.5 | 20.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CenterPoint*Venue=CVPR’212026.06 | 22 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StreamPETRBackbone=VoV-99, Modality=Camera, Image/Voxel Size=960 x 6402023.08 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.6 | 0.843 | 0.321 | 0.65 | — | — | |
| StreamPETRBackbone=V2-99, Image Size=900x6402024.02 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.6 | 0.843 | 0.321 | 0.65 | — | — | |
| StreamPETRBackbone=V2-99, Image Size=640 × 960, Input=C2026.04 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.6 | 0.843 | 0.321 | 0.65 | — | — | |
| StreamPETRBackbone=VoV-992026.04 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.6 | 0.843 | 0.321 | 0.65 | — | — | |
| StreamPETRBackbone=VoVNet-99, Input image resolution=640x960, Training subsampling strategy=10 Hz subsequences, Evaluation range=150 meters2026.04 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.6 | 0.843 | 0.321 | 0.65 | — | — | |
| StreamPETRVenue=ICCV’232026.06 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StereoMV2D-TImg Size=960 × 640, Backbone=VoVNetV2, Frames=22025.12 | 19.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 13.8 | 0.811 | 0.325 | 0.723 | — | — | |
| Sparse4Dv2Backbone=VoV-99, Modality=Camera, Image/Voxel Size=960 x 6402023.08 | 18.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 13.4 | 0.832 | 0.343 | 0.723 | — | — | |
| Sparse4Dv2Backbone=V2-99, Image Size=900x6402024.02 | 18.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 13.4 | 0.832 | 0.343 | 0.723 | — | — |