Research map / Image generation / Image restoration
Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
Bin Ren, Yawei Li, Xu Zheng, Yuqian Fu, Danda Pani Paudel, Hong Liu, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe
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 |
|---|---|---|---|
| add dynamic convolution branch (ablation) | MIRAGE-T · 3-degradation ablation (MIRAGE-T) | PSNR (dB): 32.21 -> 32.77 | Improved |
| add channel-wise MLP branch (ablation) | MIRAGE-T · 3-degradation ablation (MIRAGE-T) | PSNR (dB): 32.39 -> 32.77 | Improved |
| add explicit feature fusion instead of concatenation (ablation) | MIRAGE-T · 3-degradation ablation (MIRAGE-T) | PSNR (dB): 32.57 -> 32.77 | Improved |
| add shallow-latent contrastive learning (ablation) | MIRAGE-T · 3-degradation ablation (MIRAGE-T) | PSNR (dB): 32.63 -> 32.77 | Improved |
| align contrastive features in SPD space instead of Euclidean (ablation) | MIRAGE-T · 3-degradation ablation (MIRAGE-T) | PSNR (dB): 32.53 -> 32.77 | Improved |
| channel-wise decomposition into CNN/attention/MLP vs attention-only (ablation) | MIRAGE-T · 3-degradation ablation (MIRAGE-T) | PSNR (dB): 32.23 -> 32.77 | Improved |
| MIRAGE-S vs MoCE-IR | MIRAGE-S · All-in-one, 3 degradations (average) | PSNR (dB): 32.73 -> 32.91 | Improved |
| MIRAGE-S vs MoCE-IR | MIRAGE-S · All-in-one, 5 degradations (average) | PSNR (dB): 30.58 -> 30.68 | Improved |
| MIRAGE-T vs MoCE-IR | MIRAGE-T · All-in-one, 5 degradations (average) | PSNR (dB): 30.58 -> 30.41 | Hurt |
| MIRAGE-T vs MoCE-IR | MIRAGE-T · Mixed degradations CDD11 (average) | PSNR (dB): 29.05 -> 28.86 | Hurt |
| MIRAGE-S vs MoCE-IR on zero-shot underwater | MIRAGE-S · Zero-shot underwater enhancement | PSNR (dB): 15.91 -> 17.29 | Improved |
| MIRAGE-S vs Histoformer on RainDrop | MIRAGE-S · Adverse weather RainDrop | PSNR (dB): 33.06 -> 32.78 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- AdaIR — AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation (ICLR 2025) · better on 2 of 2 shared results
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 2 of 2 shared results
- OneRestore — OneRestore: A Universal Restoration Framework for Composite Degradation (ECCV 2024) · better on 1 of 1 shared result
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
- Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank (CVPR 2026 · similarity 0.89)
- Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration (ICLR 2026 · similarity 0.88)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · similarity 0.88)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · similarity 0.88)
- Degradation-Aware Feature Perturbation for All-in-One Image Restoration (CVPR 2025 · similarity 0.88)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · 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.
