AI Paper Atlas

Research map / Image generation / Image restoration

A Comparative Study of Image Restoration Networks for General Backbone Network Design

Xiangyu Chen, Zheyuan Li, Yuandong Pu, Yihao Liu, Jiantao Zhou, Yu Qiao, Chao Dong

ECCV 2024 · Image generation › Image restoration · approach: Priors for restoration networks · 74 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
replace half of the transposed self-attention blocks with overlapping cross-attention spatial blocksRestormer · x4 SR Manga109PSNR (dB): 31.96 -> 32.38Improved
add spatial self-attention blocks to RestormerRestormer · Denoising sigma=50 Urban100PSNR (dB): 30.02 -> 30.24Improved
add spatial self-attention blocks to RestormerRestormer · Deblurring HIDEPSNR (dB): 31.22 -> 31.76Improved
add spatial self-attention blocks to RestormerRestormer · Deraining Rain100HPSNR (dB): 31.48 -> 32.09Improved
add spatial self-attention blocks to RestormerRestormer · Deraining Test1200PSNR (dB): 33.22 -> 32.31Hurt
add spatial self-attention blocks to RestormerRestormer · Dehazing SOTS IndoorPSNR (dB): 41.97 -> 42.90Improved
add spatial self-attention blocks to RestormerRestormer · All-in-one dehazingPSNR (dB): 36.95 -> 38.24Improved
use X-Restormer (U-shape) versus plain-architecture HAT on SRX-Restormer · x4 SRPSNR (dB)Hurt
use SwinIR (plain architecture, local attention) for global-context tasksSwinIR · Dehazing SOTS IndoorPSNR (dB): 41.87 -> 29.14Hurt
train one all-in-one model across five tasks with a more general backboneX-Restormer · All-in-one restorationPSNR (dB)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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