3D Semantic Scene Completion From A Single 1
평가 지표
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mIoU | Paper Title | Repository |
|---|---|---|---|
| VoxFormer | 12.20 | VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion | |
| JS3C-Net (rgb input - reported in MonoScene paper) | 8.97 | Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion | |
| CGFormer | 16.63 | Context and Geometry Aware Voxel Transformer for Semantic Scene Completion | |
| NDC-Scene | 12.58 | NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space | |
| LMSCNet (rgb input - reported in MonoScene paper) | 7.09 | LMSCNet: Lightweight Multiscale 3D Semantic Completion | |
| 3DSketch (rgb input - reported in MonoScene paper) | 6.23 | 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior | |
| MonoScene | 11.08 | MonoScene: Monocular 3D Semantic Scene Completion | |
| OccFormer | 12.32 | OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction | |
| Symphonies | 15.04 | Symphonize 3D Semantic Scene Completion with Contextual Instance Queries |
0 of 9 row(s) selected.