The RSBlur dataset provides pairs of real and synthetic blurred images with ground truth sharp images. The dataset enables the evaluation of deblurring methods and blur synthesis methods on real-world blurred images. Training, validation, and test sets consist of 8,878, 1,120, and 3,360 blurred images, respectively.
Variants: RSBlur, RSBlur (trained on synthetic)
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Deblurring | SegDeblur | Real-World Efficient Blind Motion Deblurring … | 2024-04-18 |
| Deblurring | MLWNet | Efficient Multi-scale Network with Learnable … | 2023-12-29 |
| Deblurring | Restormer | Restormer: Efficient Transformer for High-Resolution … | 2021-11-18 |
| Deblurring | MIMO-UNet | Rethinking Coarse-to-Fine Approach in Single … | 2021-08-11 |
| Deblurring | MIMO-UNet+ | Rethinking Coarse-to-Fine Approach in Single … | 2021-08-11 |
| Deblurring | Uformer-B | Uformer: A General U-Shaped Transformer … | 2021-06-06 |
| Deblurring | MPRNet | Multi-Stage Progressive Image Restoration | 2021-02-04 |
| Deblurring | SRN-Deblur | Scale-recurrent Network for Deep Image … | 2018-02-06 |
Recent papers with results on this dataset: