3D Semantic Scene Completion On Kitti 360
评估指标
mIoU
评测结果
各个模型在此基准测试上的表现结果
模型名称 | mIoU | Paper Title | Repository |
|---|---|---|---|
| SSCNet | 16.95 | Semantic Scene Completion from a Single Depth Image | |
| VoxFormer | 11.91 | VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion | |
| Symphonies | 18.58 | Symphonize 3D Semantic Scene Completion with Contextual Instance Queries | |
| LMSCNet | 13.65 | LMSCNet: Lightweight Multiscale 3D Semantic Completion | |
| TPVFormer | 13.64 | Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction | |
| MonoScene | 12.31 | MonoScene: Monocular 3D Semantic Scene Completion | |
| OccFormer | 13.81 | OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction |
0 of 7 row(s) selected.