We propose a large-scale benchmark here, which contains a total of 6,461 mirror images with ground truth annotations.
Variants: PMD
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Segmentation | SAM2-UNet | SAM2-UNet: Segment Anything 2 Makes … | 2024-08-16 |
| Image Segmentation | HetNet | Efficient Mirror Detection via Multi-level … | 2022-11-28 |
| Image Segmentation | MirrorNet | Where Is My Mirror? | 2019-08-24 |
Recent papers with results on this dataset: