3D Object Detection
3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.
( Image credit: AVOD )
Papers
Showing 1–10 of 1576 papers
All datasetsnuScenesScanNetV2SUN-RGBD valKITTI Cars EasyKITTI Cars HardnuScenes Camera OnlyKITTI Cars Easy valKITTI Cars Moderate valnuscenes Camera-RadarView-of-Delft (val)KITTI Cars Hard valDAIR-V2X-I
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DEST (based on V-DETR) (TTA) | mAP@0.5 | 67.9 | — | Unverified |
| 2 | UniDet3D | mAP@0.5 | 66.1 | — | Unverified |
| 3 | V-DETR | mAP@0.5 | 65.9 | — | Unverified |
| 4 | UDeerMvDETR | mAP@0.5 | 65.8 | — | Unverified |
| 5 | OneFormer3D | mAP@0.5 | 65.3 | — | Unverified |
| 6 | BFL | mAP@0.5 | 65.3 | — | Unverified |
| 7 | Swin3D-L+CAGroup3D | mAP@0.5 | 63.2 | — | Unverified |
| 8 | QueryFormer | mAP@0.5 | 61.7 | — | Unverified |
| 9 | CAGroup3D | mAP@0.5 | 61.3 | — | Unverified |
| 10 | PBNet | mAP@0.5 | 60.1 | — | Unverified |