3D Object Detection on View-of-Delft (VoD) (val)
61.5AP (Car, Entire Area)SIFormer
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SIFormerModality=Radar+Camera, Leverage LiDAR during training=true, Trained with pseudo labels=true2026.05 | 61.5 | 51.4 | 77.1 | 63.3 | 90.7 | 68.6 | 89.9 | 83.1 | — | — | — | — | — | — | 6.9 | |
| SIFormerInput=R+C, Extra LiDAR=true, FPS=6.92026.02 | 61.49 | 51.39 | 77.09 | 63.32 | — | — | — | — | 90.67 | 68.6 | 89.92 | 83.06 | — | — | — | |
| MSSF-PPModality=Radar+Camera2026.05 | 61 | 51.3 | 77.7 | 63.3 | 90.6 | 60.4 | 88.4 | 79.8 | — | — | — | — | — | 13.9 | — | |
| CVFusionModality=Radar+Camera2026.05 | 60.9 | 57.9 | 77.5 | 65.4 | 89.9 | 68.8 | 88.6 | 82.4 | — | — | — | — | — | 5.4 | — | |
| RaGSModality=Radar+Camera, Leverage LiDAR during training=true, Trained with pseudo labels=true2026.05 | 58.2 | 50.8 | 76.6 | 61.9 | 88.2 | 61.7 | 95.1 | 81.6 | — | — | — | — | — | — | 10.5 | |
| RCGDet3DModality=Radar+Camera2026.05 | 56.5 | 61.1 | 79.3 | 65.6 | 87.5 | 66.6 | 96.1 | 83.4 | — | — | — | — | 19.9 | — | — | |
| SIFormerModality=Radar+Camera, Trained with pseudo labels=true2026.05 | 53.8 | 50.7 | 76.1 | 60.2 | 81.2 | 60.5 | 90.2 | 77.3 | — | — | — | — | — | — | 6.9 | |
| SIFormerInput=R+C, Extra LiDAR=false, FPS=6.92026.02 | 53.75 | 50.68 | 76.12 | 60.18 | — | — | — | — | 81.16 | 60.5 | 90.15 | 77.27 | — | — | — | |
| SGDet3DModality=Radar+Camera, Leverage LiDAR during training=true, Trained with pseudo labels=true2026.05 | 53.2 | 50 | 76.1 | 59.8 | 81.1 | 60.9 | 90.2 | 77.4 | — | — | — | — | — | — | 9.2 | |
| SGDet3DInput=R+C, Extra LiDAR=true, FPS=9.22026.02 | 53.16 | 49.98 | 76.11 | 59.75 | — | — | — | — | 81.13 | 60.91 | 90.22 | 77.42 | — | — | — | |
| HyDRaModality=Radar+Camera2026.05 | 52.8 | 56.6 | 73.3 | 60.9 | 80.7 | 62.9 | 87.4 | 77 | — | — | — | — | — | — | — | |
| IS-FusionInput=R+C, Extra LiDAR=false, FPS=15.12026.02 | 48.57 | 46.17 | 68.48 | 54.4 | — | — | — | — | 80.42 | 55.5 | 88.33 | 74.75 | — | — | — | |
| LXLv2Modality=Radar+Camera2026.05 | 47.8 | 49.3 | 77.2 | 58.1 | — | — | — | — | — | — | — | — | 6.5 | — | — | |
| RaCFormerInput=C+R2024.12 | 47.3 | 46.21 | 69.8 | 54.44 | 89.26 | 56.78 | 89.67 | 78.57 | — | — | — | — | — | — | — | |
| LGDDModality=Radar2026.05 | 46.9 | 41.6 | 72 | 53.5 | 78.6 | 51.1 | 86.9 | 72.2 | — | — | — | — | — | 25.1 | — | |
| FUTR3DInput=R+C, Extra LiDAR=false, FPS=7.32026.02 | 46.01 | 35.11 | 65.98 | 49.03 | — | — | — | — | 78.66 | 43.1 | 86.19 | 69.32 | — | — | — | |
| LXLInput=R+C, Extra LiDAR=false, FPS=6.12026.02 | 42.33 | 49.48 | 77.12 | 56.31 | — | — | — | — | 72.18 | 58.3 | 88.31 | 72.93 | — | — | — | |
| SMURFInput=R, Extra LiDAR=false2026.02 | 42.31 | 39.09 | 71.5 | 50.97 | — | — | — | — | 71.74 | 50.54 | 86.87 | 69.72 | — | — | — | |
| SMURFModality=Radar2026.05 | 42.3 | 39.1 | 71.5 | 51 | 71.7 | 50.5 | 86.9 | 69.7 | — | — | — | — | 30 | — | — | |
| MAFF-NetModality=Radar2026.05 | 42.3 | 46.8 | 74.7 | 54.6 | 72.3 | 57.8 | 87.4 | 72.5 | — | — | — | — | — | — | 28.7 | |
| LXLModality=Radar+Camera2026.05 | 42.3 | 49.5 | 77.1 | 56.3 | 72.2 | 58.3 | 88.3 | 72.9 | — | — | — | — | 6.1 | — | — | |
| SCKDModality=Radar, Leverage LiDAR during training=true2026.05 | 41.9 | 43.5 | 70.8 | 52.1 | 77.5 | 51.1 | 86.9 | 71.8 | — | — | — | — | — | — | 39.3 | |
| RCFusionInput=C+R2024.12 | 41.7 | 38.95 | 68.31 | 49.65 | 71.87 | 47.5 | 88.33 | 69.23 | — | — | — | — | — | — | — | |
| RCFusionInput=R+C, Extra LiDAR=false, FPS=92026.02 | 41.7 | 38.95 | 68.31 | 49.65 | — | — | — | — | 71.87 | 47.5 | 88.33 | 69.23 | — | — | — | |
| RCFusionModality=Radar+Camera2026.05 | 41.7 | 39 | 68.3 | 49.7 | 71.9 | 47.5 | 88.3 | 69.2 | — | — | — | — | — | 9 | — | |
| RadarGaussianDet3DModality=Radar2026.05 | 40.7 | 42.4 | 73 | 52 | 71.2 | 51.7 | 89 | 70.6 | — | — | — | — | 83.2 | — | — | |
| RCBEVDetInput=C+R2024.12 | 40.63 | 38.86 | 70.48 | 49.99 | 72.48 | 49.89 | 87.01 | 69.8 | — | — | — | — | — | — | — | |
| RCBEVDetInput=R+C, Extra LiDAR=false2026.02 | 40.63 | 38.86 | 70.48 | 49.99 | — | — | — | — | 72.48 | 49.89 | 87.01 | 69.8 | — | — | — | |
| RadarGaussianDet3D+Modality=Radar2026.05 | 39.9 | 45.9 | 75 | 53.6 | 71 | 52.3 | 89 | 70.8 | — | — | — | — | 77.5 | — | — | |
| RadarPillarNetInput=R2024.12 | 39.3 | 35.1 | 63.63 | 46.01 | 71.65 | 42.8 | 83.14 | 65.86 | — | — | — | — | — | — | — | |
| RadarPillarNetInput=R, Extra LiDAR=false, FPS=98.82026.02 | 39.3 | 35.1 | 63.63 | 46.01 | — | — | — | — | 71.65 | 42.8 | 83.14 | 65.86 | — | — | — | |
| PointPillarsModality=Radar2026.05 | 38.8 | 34.4 | 66.9 | 46.7 | 71.9 | 45.1 | 88.4 | 67.8 | — | — | — | — | 78.4 | 178.4 | 187 | |
| BEVFusionInput=R+C, Extra LiDAR=false, FPS=7.12026.02 | 37.85 | 40.96 | 68.95 | 49.25 | — | — | — | — | 70.21 | 45.86 | 89.48 | 68.52 | — | — | — | |
| PointPillarsInput=R2024.12 | 37.06 | 35.04 | 63.44 | 45.18 | 70.15 | 47.22 | 85.07 | 67.48 | — | — | — | — | — | — | — | |
| LXL - RInput=R, Extra LiDAR=false, FPS=44.72026.02 | 32.75 | 39.65 | 68.13 | 46.84 | — | — | — | — | 70.26 | 47.34 | 87.93 | 68.51 | — | — | — | |
| ImVoxelNetInput=C, Extra LiDAR=false, FPS=11.12026.02 | 19.35 | 5.62 | 17.53 | 14.17 | — | — | — | — | 49.52 | 9.68 | 28.97 | 29.39 | — | — | — |