Research map / Image generation / Image restoration
Image Restoration via Multi-Domain Learning
Xingyu Jiang, Ning Gao, Xiuhui Zhang, Hongkun Dou, Shaowen Fu, Xiaoqing Zhong, Hongjue Li, Yue Cheng Deng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| SWFormer-l vs SFHformer on low-light | SWFormer · LOL-v1 | PSNR (dB): +1.41 dB | Improved |
| SWFormer-l vs SFHformer on heavy haze | SWFormer · DENSE-HAZE | PSNR (dB): 17.84 -> 18.38 | Improved |
| SWFormer-l vs SFHformer on generalization | SWFormer · HIDE (trained on GoPro) | PSNR (dB): 31.66 -> 32.07 | Improved |
| SWFormer vs SFHformer on desnowing | SWFormer · CSD/SRRS/Snow100K | PSNR (dB): +0.4 dB | Improved |
| SWFormer-l vs ShadowDiffusion on shadow region | SWFormer · AISTD shadow region | PSNR (dB): 39.82 -> 40.45 | Improved |
| SWFormer-l vs EMRDM on heavy cloud | SWFormer · CUHK-CR2 | PSNR (dB): 24.594 -> 25.737 | Improved |
| scale model from small to large (ablation) | SWFormer · Rain200L | PSNR (dB): 42.01 -> 42.70 | Improved |
| SWFormer-l vs best defocus baseline on DPDD | SWFormer · DPDD | PSNR (dB): 26.272 -> 26.220 | No clear effect |
| replace self-attention with spatial-wavelet-fourier mixer (SWFormer-s vs SFHformer) | SWFormer-s · Rain200L 256x256 latency | inference time (ms): 65.2 -> 25.9 | Improved |
| SWFormer-s vs DRSformer on 4K images | SWFormer-s · 4K-Rain13k | inference time (ms): 2682 -> 40 | Improved |
| SWFormer-m vs SFHformer complexity | SWFormer-m · deraining | parameters and FLOPs: 21.4% of Params, 54.6% of FLOPs | Improved |
| use lossless multi-input multi-output instead of SISO or MIMO (ablation) | SWFormer · restoration benchmarks | restoration performance | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ShadowDiffusion — ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal (CVPR 2023) · better on 1 of 1 shared result
- RetinexFormer — Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- When Fast Fourier Transform Meets Transformer for Image Restoration (ECCV 2024 · similarity 0.91)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.88)
- Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration (CVPR 2024 · similarity 0.88)
- Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement (AAAI 2024 · similarity 0.88)
- Rethinking Multi-Scale Representations in Deep Deraining Transformer (AAAI 2024 · similarity 0.87)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
