Metric: mIoU (higher is better)
| # | Model↕ | mIoU▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | CGFormer | 16.63 | No | Context and Geometry Aware Voxel Transformer for... | 2024-05-22 | Code |
| 2 | Symphonies | 15.04 | No | Symphonize 3D Semantic Scene Completion with Con... | 2023-06-27 | Code |
| 3 | NDC-Scene | 12.58 | No | NDC-Scene: Boost Monocular 3D Semantic Scene Com... | 2023-09-26 | Code |
| 4 | OccFormer | 12.32 | No | OccFormer: Dual-path Transformer for Vision-base... | 2023-04-11 | Code |
| 5 | VoxFormer | 12.2 | No | VoxFormer: Sparse Voxel Transformer for Camera-b... | 2023-02-23 | Code |
| 6 | MonoScene | 11.08 | No | MonoScene: Monocular 3D Semantic Scene Completion | 2021-12-01 | Code |
| 7 | JS3C-Net (rgb input - reported in MonoScene paper) | 8.97 | No | Sparse Single Sweep LiDAR Point Cloud Segmentati... | 2020-12-07 | Code |
| 8 | LMSCNet (rgb input - reported in MonoScene paper) | 7.09 | No | LMSCNet: Lightweight Multiscale 3D Semantic Comp... | 2020-08-24 | Code |
| 9 | 3DSketch (rgb input - reported in MonoScene paper) | 6.23 | No | 3D Sketch-aware Semantic Scene Completion via Se... | 2020-03-31 | Code |