Object Detection In Indoor Scenes On Sun Rgb
Metrics
AP 0.5
Results
Performance results of various models on this benchmark
Model Name | AP 0.5 | Paper Title | Repository |
|---|---|---|---|
| YONOD + CPPM (RGB + Depth) | 58.1 | Unified Object Detector for Different Modalities based on Vision Transformers | |
| 2D - Driven (RGB) | 49.7 | 2D-Driven 3D Object Detection in RGB-D Images | - |
| RGB-D RCNN (RGB + Depth) | 44.2 | Learning Rich Features from RGB-D Images for Object Detection and Segmentation | |
| Frustum Pointnet (RGB) | 56.8 | Frustum PointNets for 3D Object Detection from RGB-D Data | |
| simCrossTrans with Swin Transformer (Point Cloud only) | 55.8 | simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers | |
| Frustum VoxNet (Depth only) | 42.8 | Frustum VoxNet for 3D object detection from RGB-D or Depth images | - |
| Frustum VoxNet (RGB) | 47.9 | Frustum VoxNet for 3D object detection from RGB-D or Depth images | - |
0 of 7 row(s) selected.