| Paper | Code | mIoU | Pixel Accuracy | mAcc | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers | ✓ Link | 62.1 | 82.6 | CMX (SegFormer-B4) | 2022-03-09 | |
| CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers | ✓ Link | 61.2 | 82.3 | CMX (SegFormer-B2) | 2022-03-09 | |
| ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation | ✓ Link | 60.6 | 82.7 | 70.0 | ShapeConv-101 | 2021-08-24 |
| Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation | ✓ Link | 57.16 | Linear Fusion (Segformer B2) | 2023-04-21 | ||
| Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images | 52.9 | 76.5 | 62.3 | MMAF-Net-152 | 2019-12-25 | |
| Depth-aware CNN for RGB-D Segmentation | ✓ Link | 39.5 | 65.4 | 55.5 | Depth-aware CNN | 2018-03-19 |