Haze4k is a synthesized dataset with 4,000 hazy images, in which each hazy image has the associate ground truths of a latent clean image, a transmission map, and an atmospheric light ma
Variants: Haze4k
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Dehazing | CasDyF-Net | CasDyF-Net: Image Dehazing via Cascaded … | 2024-09-13 |
| Image Dehazing | MixDehazeNet | MixDehazeNet : Mix Structure Block … | 2023-05-28 |
| Image Dehazing | DEA-Net-CR | DEA-Net: Single image dehazing based … | 2023-01-12 |
| Image Dehazing | gUNet-D | Rethinking Performance Gains in Image … | 2022-09-23 |
| Image Dehazing | PMNet | Perceiving and Modeling Density is … | 2021-11-18 |
| Image Dehazing | DMT-Net | From Synthetic to Real: Image … | 2021-08-06 |
| Image Dehazing | MSBDN | Multi-Scale Boosted Dehazing Network with … | 2020-04-28 |
| Image Dehazing | FFA-Net | FFA-Net: Feature Fusion Attention Network … | 2019-11-18 |
| Image Dehazing | GDNet | GridDehazeNet: Attention-Based Multi-Scale Network for … | 2019-08-08 |
Recent papers with results on this dataset: