3D Object Detection On Rope3D
Metrics
AP@0.7
Results
Performance results of various models on this benchmark
Model Name | AP@0.7 | Paper Title | Repository |
|---|---|---|---|
| CoBEV | 52.72 | CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity | - |
| M3D-RPN+(G) | 16.75 | M3D-RPN: Monocular 3D Region Proposal Network for Object Detection | - |
| BEVFormer | 24.64 | BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision | - |
| BEVHeight | 45.73 | BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection | - |
| MonoUNI | 75.27 | MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues | |
| Kinematic3D+(G) | 17.74 | Kinematic 3D Object Detection in Monocular Video | - |
| BEVDepth | 42.56 | BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection | - |
| MonoDLE+(G) | 13.58 | Delving into Localization Errors for Monocular 3D Object Detection | - |
0 of 8 row(s) selected.