AI Paper Atlas

Research map / Image generation / Image restoration

MambaIR: A Simple Baseline for Image Restoration with State-Space Model

Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, Shu-Tao Xia

ECCV 2024 · Image generation › Image restoration · approach: Efficient restoration architectures · 865 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 Transformer SwinIR with MambaIR backbone on classic SRMambaIR · Manga109 x2 classic SRPSNR (dB): 39.92 -> 40.28Improved
replace SwinIR-light with MambaIR-lightMambaIR-light · Manga109 x4 lightweight SRPSNR (dB): 30.92 -> 30.94Improved
replace SwinIR with MambaIR for Gaussian denoisingMambaIR · Gaussian color denoising Urban100 sigma=50PSNR (dB): 29.82 -> 30.30Improved
MambaIR vs Restormer on real denoising SIDDMambaIR · Real denoising SIDDPSNR (dB): 40.02 -> 39.89No clear effect
add local convolution and channel attention to vanilla Mamba block (ablation)MambaIR RSSB · image SR ablationPSNRImproved
use Conv+ChannelAttention instead of MLP after VSSM (ablation)MambaIR RSSB · image SR ablationPSNRImproved
use four-direction scanning instead of one or two directions (ablation)MambaIR VSSM · image SR ablationPSNRImproved
use MambaIR instead of full attention for complexity scalingMambaIR · computational complexity vs input sizecompute scalingImproved

Later papers that compared with this method

6 later accepted papers report MambaIR as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

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