Monocular 3D Object Detection On Sun Rgb D
评估指标
AP@0.15 (10 / NYU-37)
AP@0.15 (NYU-37)
评测结果
各个模型在此基准测试上的表现结果
模型名称 | AP@0.15 (10 / NYU-37) | AP@0.15 (NYU-37) | Paper Title | Repository |
|---|---|---|---|---|
| IM3D | 45.21 | 24.10 | Holistic 3D Scene Understanding from a Single Image with Implicit Representation | |
| Total3D joint | 26.38 | 14.28 | Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image | |
| PerspectiveNet | - | - | PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points | - |
| Total3D w/o. joint | 23.32 | 13.25 | Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image | |
| Cooperative | 23.65 | 12.23 | Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation | |
| ImVoxelNet | 42.69 | 21.08 | ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection | |
| Holistic | 14.01 | - | Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image |
0 of 7 row(s) selected.