Command Palette
Search for a command to run...
3D Object Detection On Nuscenes Lidar Only
Metrics
NDS
NDS (val)
mAP
mAP (val)
Results
Performance results of various models on this benchmark
| Paper Title | Repository | |||||
|---|---|---|---|---|---|---|
| LION | 73.9 | 72.1 | 69.8 | 68.0 | LION: Linear Group RNN for 3D Object Detection in Point Clouds | |
| DSVT | 72.7 | 71.1 | 68.4 | 66.4 | DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets | |
| PillarNet | 71.4 | - | 66.0 | - | PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection | |
| Transfusion | 70.2 | 70.1 | 65.5 | 65.1 | TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers | |
| CenterPoint | 67.3 | 66.8 | 60.3 | 59.6 | Center-based 3D Object Detection and Tracking | |
| CBGS | 63.3 | 62.3 | 52.8 | 50.6 | Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection | |
| PointPillar | 45.3 | - | 30.5 | - | PointPillars: Fast Encoders for Object Detection from Point Clouds |
0 of 7 row(s) selected.