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
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 |
|---|---|---|---|
| replace Transformer SwinIR with MambaIR backbone on classic SR | MambaIR · Manga109 x2 classic SR | PSNR (dB): 39.92 -> 40.28 | Improved |
| replace SwinIR-light with MambaIR-light | MambaIR-light · Manga109 x4 lightweight SR | PSNR (dB): 30.92 -> 30.94 | Improved |
| replace SwinIR with MambaIR for Gaussian denoising | MambaIR · Gaussian color denoising Urban100 sigma=50 | PSNR (dB): 29.82 -> 30.30 | Improved |
| MambaIR vs Restormer on real denoising SIDD | MambaIR · Real denoising SIDD | PSNR (dB): 40.02 -> 39.89 | No clear effect |
| add local convolution and channel attention to vanilla Mamba block (ablation) | MambaIR RSSB · image SR ablation | PSNR | Improved |
| use Conv+ChannelAttention instead of MLP after VSSM (ablation) | MambaIR RSSB · image SR ablation | PSNR | Improved |
| use four-direction scanning instead of one or two directions (ablation) | MambaIR VSSM · image SR ablation | PSNR | Improved |
| use MambaIR instead of full attention for complexity scaling | MambaIR · computational complexity vs input size | compute scaling | Improved |
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.
- Compression Artifacts Removal for VVC with Frequency Domain Mixture of Experts Network (AAAI 2026 · better on 5 of 5 shared results)
- UniH3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration (ECCV 2026 · better on 2 of 2 shared results)
- TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond (CVPR 2025 · better on 5 of 5 shared results)
- MambaIRv2: Attentive State Space Restoration (CVPR 2025 · better on 4 of 4 shared results)
- EAMamba: Efficient All-Around Vision State Space Model for Image Restoration (ICCV 2025 · better on 3 of 4 shared results)
- MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration (CVPR 2025 · better on 2 of 2 shared results)
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 4 shared results
- SRFormer — SRFormer: Permuted Self-Attention for Single Image Super-Resolution (ICCV 2023) · better on 2 of 3 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
- MambaIRv2: Attentive State Space Restoration (CVPR 2025 · similarity 0.92)
- MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration (CVPR 2025 · similarity 0.91)
- Demystify Mamba in Vision: A Linear Attention Perspective (NeurIPS 2024 · similarity 0.89)
- Vision Mamba Mender (NeurIPS 2024 · similarity 0.89)
- MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025 · similarity 0.88)
- ACL: Activating Capability of Linear Attention for Image Restoration (CVPR 2025 · similarity 0.88)
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.
