Research map / Image generation / Image restoration
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
Yu-Cheng Lin, Yu-Syuan Xu, Hao-Wei Chen, Hsien-Kai Kuo, Chun-Yi Lee
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 2DSS with multi-head selective scan MHSSM (ablation) | EAMamba · Urban100 denoising sigma=50 | PSNR: 30.08 -> 29.95 | Hurt |
| replace 2DSS with MHSSM (ablation) | EAMamba · Urban100 denoising | FLOPs: 286 -> 137 | Improved |
| add all-around scanning on top of MHSSM (ablation) | EAMamba · Urban100 denoising sigma=50 | PSNR: 29.95 -> 30.01 | Improved |
| add all-around scanning on top of MHSSM (ablation) | EAMamba · Urban100 denoising sigma=25 | PSNR: 32.89 -> 32.93 | Improved |
| use all-around scan instead of single 2D scan (ablation) | EAMamba · SIDD | PSNR: 39.80 -> 39.87 | Improved |
| use all-around scan instead of Hilbert scan (ablation) | EAMamba · SIDD | PSNR: 39.74 -> 39.87 | Improved |
| combine 2D with Z-order instead of 2D + diagonal (ablation) | EAMamba · SIDD | PSNR: 39.87 -> 39.82 | Hurt |
| combine 2D with Hilbert instead of 2D + diagonal (ablation) | EAMamba · GoPro | PSNR: 33.58 -> 33.66 | Improved |
| add Z-order scan to 2D + diagonal (ablation) | EAMamba · SOTS-Indoor | PSNR: 43.19 -> 43.37 | Improved |
| add Z-order scan to 2D + diagonal (ablation) | EAMamba · SIDD | PSNR: 39.87 -> 39.83 | Hurt |
| add channel MLP (Simple FFN) to MambaFormer block (ablation) | EAMamba · Urban100 denoising sigma=15 | PSNR: 34.98 -> 35.10 | Improved |
| use GDFN instead of Simple FFN as channel MLP (ablation) | EAMamba · Urban100 denoising sigma=50 | PSNR: 30.01 -> 30.08 | Improved |
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 4 of 5 shared results
- MambaIR — MambaIR: A Simple Baseline for Image Restoration with State-Space Model (ECCV 2024) · better on 3 of 4 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
- MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration (CVPR 2025 · similarity 0.91)
- Vision Mamba Mender (NeurIPS 2024 · similarity 0.91)
- MambaIRv2: Attentive State Space Restoration (CVPR 2025 · similarity 0.90)
- Demystify Mamba in Vision: A Linear Attention Perspective (NeurIPS 2024 · similarity 0.89)
- ACL: Activating Capability of Linear Attention for Image Restoration (CVPR 2025 · similarity 0.88)
- Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model (NeurIPS 2024 · 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.
