UPLight is an underwater RGB-Polarization multimodal semantic segmentation dataset with 12 typical underwater semantic classes.
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Semantic Segmentation | ShareCMP (B2 RGB-FP) | ShareCMP: Polarization-Aware RGB-P Semantic Segmentation | 2023-12-06 |
| Semantic Segmentation | CMX (B2 RGB-AoLP) | CMX: Cross-Modal Fusion for RGB-X … | 2022-03-09 |
| Semantic Segmentation | CMX (B2 RGB-DoLP) | CMX: Cross-Modal Fusion for RGB-X … | 2022-03-09 |
| Semantic Segmentation | SegFormer-B2 (RGB) | SegFormer: Simple and Efficient Design … | 2021-05-31 |
| Semantic Segmentation | EAFNet (RGB-AoLP) | Polarization-driven Semantic Segmentation via Efficient … | 2020-11-26 |
| Semantic Segmentation | EAFNet (RGB-DoLP) | Polarization-driven Semantic Segmentation via Efficient … | 2020-11-26 |
Recent papers with results on this dataset: