AI Paper Atlas

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

TPAMI 2026 · Image generation › Image restoration · approach: Efficient restoration architectures · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
SWFormer-l vs SFHformer on low-lightSWFormer · LOL-v1PSNR (dB): +1.41 dBImproved
SWFormer-l vs SFHformer on heavy hazeSWFormer · DENSE-HAZEPSNR (dB): 17.84 -> 18.38Improved
SWFormer-l vs SFHformer on generalizationSWFormer · HIDE (trained on GoPro)PSNR (dB): 31.66 -> 32.07Improved
SWFormer vs SFHformer on desnowingSWFormer · CSD/SRRS/Snow100KPSNR (dB): +0.4 dBImproved
SWFormer-l vs ShadowDiffusion on shadow regionSWFormer · AISTD shadow regionPSNR (dB): 39.82 -> 40.45Improved
SWFormer-l vs EMRDM on heavy cloudSWFormer · CUHK-CR2PSNR (dB): 24.594 -> 25.737Improved
scale model from small to large (ablation)SWFormer · Rain200LPSNR (dB): 42.01 -> 42.70Improved
SWFormer-l vs best defocus baseline on DPDDSWFormer · DPDDPSNR (dB): 26.272 -> 26.220No clear effect
replace self-attention with spatial-wavelet-fourier mixer (SWFormer-s vs SFHformer)SWFormer-s · Rain200L 256x256 latencyinference time (ms): 65.2 -> 25.9Improved
SWFormer-s vs DRSformer on 4K imagesSWFormer-s · 4K-Rain13kinference time (ms): 2682 -> 40Improved
SWFormer-m vs SFHformer complexitySWFormer-m · derainingparameters and FLOPs: 21.4% of Params, 54.6% of FLOPsImproved
use lossless multi-input multi-output instead of SISO or MIMO (ablation)SWFormer · restoration benchmarksrestoration performanceImproved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy