📊 Showing 7 results | 📏 Metric: mIoU
| Rank | Model | Paper | mIoU | Date | Code |
|---|---|---|---|---|---|
| 1 | Symphonies | Symphonize 3D Semantic Scene Completion with Contextual Instance Queries | 18.58 | 2023-06-27 | 📦 hustvl/symphonies |
| 2 | SSCNet | Semantic Scene Completion from a Single Depth Image | 16.95 | 2016-11-28 | 📦 facebookresearch/House3D 📦 shurans/sscnet 📦 krrish94/ssc |
| 3 | OccFormer | OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction | 13.81 | 2023-04-11 | 📦 zhangyp15/occformer |
| 4 | LMSCNet | LMSCNet: Lightweight Multiscale 3D Semantic Completion | 13.65 | 2020-08-24 | 📦 astra-vision/lmscnet 📦 cv-rits/LMSCNet 📦 umich-curly/3dmapping |
| 5 | TPVFormer | Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction | 13.64 | 2023-02-15 | 📦 open-mmlab/mmdetection3d 📦 wzzheng/tpvformer 📦 happytianhao/tade |
| 6 | MonoScene | MonoScene: Monocular 3D Semantic Scene Completion | 12.31 | 2021-12-01 | 📦 astra-vision/monoscene 📦 cv-rits/MonoScene |
| 7 | VoxFormer | VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion | 11.91 | 2023-02-23 | 📦 nvlabs/voxformer |