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

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

23 Feb 2024arXiv:2402.15648archive 2025-07-28

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

Recent years have seen significant advancements in image restoration, largely attributed to the development of modern deep neural networks, such as CNNs and Transformers. However, existing restoration backbones often face the dilemma between global receptive fields and efficient computation, hindering their application in practice. Recently, the Selective Structured State Space Model, especially the improved version Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a way to resolve the above dilemma. However, the standard Mamba still faces certain challenges in low-level vision such as local pixel forgetting and channel redundancy. In this work, we introduce a simple but effective baseline, named MambaIR, which introduces both local enhancement and channel attention to improve the vanilla Mamba. In this way, our MambaIR takes advantage of the local pixel similarity and reduces the channel redundancy. Extensive experiments demonstrate the superiority of our method, for example, MambaIR outperforms SwinIR by up to 0.45dB on image SR, using similar computational cost but with a global receptive field. Code is available at \url{https://github.com/csguoh/MambaIR}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.15648")

Code

Syntology Ran 11 of 15 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 5 ran; community (archive-listed): 7 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

csguoh/mambair officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
iridescentttt/SynQT mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 11 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3ran · fixture could not drive it
6ran
4unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

drop_path csguoh/MambaIR/analysis/model_zoo/hat.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 52d96aa31ed74a56 · report
img2windows csguoh/MambaIR/analysis/model_zoo/cat.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 15c613ecceb6aa71 · report
window_partition csguoh/MambaIR/analysis/model_zoo/hat.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 60363d0620f5778d · report
window_reverse csguoh/MambaIR/analysis/model_zoo/hat.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 4f003e9ad9b7a7cb · report
windows2img csguoh/MambaIR/analysis/model_zoo/cat.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 8cb23a62748d3b1c · report
flops_selective_scan_fn csguoh/MambaIR/analysis/utils_fvcore.py official repository unverified Apache-2.0 (permissive) · 5f390d616fb142ad · report
flops_selective_scan_ref csguoh/MambaIR/analysis/utils_fvcore.py official repository unverified Apache-2.0 (permissive) · 0b84e99fd1e93dd6 · report
import_abspy csguoh/MambaIR/analysis/utils_fvcore.py official repository unverified Apache-2.0 (permissive) · e582f87a53fb23d4 · report
Adapter iridescentttt/SynQT/synqt.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · bb483d1dc27ae6fd · report
ConditionCombineBlock iridescentttt/SynQT/synqt.py community (archive-listed) ran MIT (permissive) · ab54423c3b962f1c · report
Mlp iridescentttt/SynQT/synqt.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · cef8b4a7bdc3ecd8 · report
Mlp1 iridescentttt/SynQT/synqt.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · e406ec263d8983d2 · report
QSMAttention iridescentttt/SynQT/synqt.py community (archive-listed) ran MIT (permissive) · bba4a43c8f71523d · report
QSMBlock iridescentttt/SynQT/synqt.py community (archive-listed) ran MIT (permissive) · d643bf97deee36bb · report
SynQT iridescentttt/SynQT/synqt.py community (archive-listed) unverified MIT (permissive) · 76fe1ca9c7cf2ce4 · report

Tasks

Image RestorationImage Super-ResolutionMamba

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution Set14 - 4x upscaling MambaIR PSNR 29.20 #20 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling MambaIR SSIM 0.7961 #20 of 104 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections