DELIVER is an arbitrary-modal segmentation benchmark, covering Depth, LiDAR, multiple Views, Events, and RGB. Aside from this, the dataset is also used in four severe weather conditions as well as five sensor failure cases to exploit modal complementarity and resolve partial outages. It is designed for the tasks of arbitrary-modal semantic segmentation.
Source: Delivering Arbitrary-Modal Semantic Segmentation
Image Source: https://arxiv.org/pdf/2303.01480v1.pdf
Variants: DELIVER, DeLiVER , DeLiVER test
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Semantic Segmentation | CAFuser | CAFuser: Condition-Aware Multimodal Fusion for … | 2024-10-14 |
| Semantic Segmentation | GeminiFusion | GeminiFusion: Efficient Pixel-wise Multimodal Fusion … | 2024-06-03 |
| Semantic Segmentation | CMNeXt (RGB-D-E-LiDAR) | Delivering Arbitrary-Modal Semantic Segmentation | 2023-03-02 |
| Semantic Segmentation | CMNeXt (RGB-D-LiDAR) | Delivering Arbitrary-Modal Semantic Segmentation | 2023-03-02 |
| Semantic Segmentation | CMNeXt (RGB-D-Event) | Delivering Arbitrary-Modal Semantic Segmentation | 2023-03-02 |
| Semantic Segmentation | CMNeXt (RGB-Depth) | Delivering Arbitrary-Modal Semantic Segmentation | 2023-03-02 |
| Semantic Segmentation | CMNeXt (RGB-LiDAR) | Delivering Arbitrary-Modal Semantic Segmentation | 2023-03-02 |
| Semantic Segmentation | CMNeXt (RGB-Event) | Delivering Arbitrary-Modal Semantic Segmentation | 2023-03-02 |
| Semantic Segmentation | SegFormer | SegFormer: Simple and Efficient Design … | 2021-05-31 |
Recent papers with results on this dataset: