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 | MonoUNI | AP|R40(moderate) | 87.2 | — | Unverified |
| 2 | CoBEV | AP|R40(moderate) | 69.6 | — | Unverified |
| 3 | BEVHeight | AP|R40(moderate) | 65.8 | — | Unverified |
| 4 | BEVDepth | AP|R40(moderate) | 63.6 | — | Unverified |
| 5 | CBR | AP|R40(moderate) | 60.1 | — | Unverified |
| 6 | PointPillars | AP|R40(moderate) | 54 | — | Unverified |
| 7 | MVXNet | AP|R40(moderate) | 53.7 | — | Unverified |
| 8 | BEVFormer | AP|R40(moderate) | 50.7 | — | Unverified |
| 9 | ImVoxelNet | AP|R40(moderate) | 37.6 | — | Unverified |