mlsanityData to 7 Oct 2026

ClusIR: Towards Cluster-Guided All-in-One Image Restoration

arXiv 2512.10948 ↗First posted 11 Dec 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often fail to explicitly model degradation types and struggle to adapt their restoration behavior to complex or mixed degradations. To address these issues, we propose ClusIR, a Cluster-Guided Image Restoration framework that explicitly models degradation semantics through learnable clustering and propagates cluster-aware cues across spatial and frequency domains for adaptive restoration. Specifically, ClusIR comprises two key components: a Probabilistic Cluster-Guided Routing Mechanism (PCGRM) and a Degradation-Aware Frequency Modulation Module (DAFMM). The proposed PCGRM disentangles degradation recognition from expert activation, enabling discriminative degradation perception and stable expert routing. Meanwhile, DAFMM leverages the cluster-guided priors to perform adaptive frequency decomposition and targeted modulation, collaboratively refining structural and textural representations for higher restoration fidelity. The cluster-guided synergy seamlessly bridges semantic cues with frequency-domain modulation, empowering ClusIR to attain remarkable restoration results across a wide range of degradations. Extensive experiments on diverse benchmarks validate that ClusIR reaches competitive performance under several scenarios.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 61 of its 86 references that are in the map. First posted on arXiv 11 Dec 2025.

Builds on

61 of 86 references.

References · 61

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  8. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  9. 2022Simple Baselines for Image Restorationcited by 701
  10. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  11. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  12. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
38 more
  1. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  2. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  3. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  4. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  5. 2022Vision Transformers for Single Image Dehazingcited by 255
  6. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  7. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  8. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  9. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  10. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 204
  11. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  12. 2022Stripformer: Strip Transformer for Fast Image Deblurringcited by 139
  13. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  14. 2019Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Rainingcited by 117
  15. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 113
  16. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  17. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  18. 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurringcited by 87
  19. 2020FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazingcited by 79
  20. 2022Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learningcited by 78
  21. 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 78
  22. 2023ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restorationcited by 77
  23. 2020Understanding SSIMcited by 75
  24. 2024Restoring Images in Adverse Weather Conditions via Histogram Transformercited by 73
  25. 2024HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Modelcited by 72
  26. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restorationcited by 72
  27. 2023GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditionscited by 62
  28. 2024Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restorationcited by 60
  29. 2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
  30. 2023Neural Degradation Representation Learning for All-In-One Image Restorationcited by 46
  31. 2025Degradation-Aware Feature Perturbation for All-in-One Image Restorationcited by 39
  32. 2023Language-driven All-in-one Adverse Weather Removalcited by 36
  33. 2022Adaptive Dynamic Filtering Network for Image Denoisingcited by 27
  34. 2023All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representationcited by 21
  35. 2024Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restorationcited by 18
  36. 2024Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restorationcited by 18
  37. 2023Precise Facial Landmark Detection by Reference Heatmap Transformercited by 16
  38. 2023Multi-task Image Restoration Guided By Robust DINO Featurescited by 14

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoningcited by 2
  2. 2026FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulationcited by 1
  3. 2026QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibrationcited by 0
  4. 2026FAHCD-Net: Frequency-Adaptive Heatmap-Conditional Diffusion Networks for Robust Facial Landmark Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
  2. 2026Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
  3. 2026UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
  4. 2024Training-Free Large Model Priors for Multiple-in-One Image Restoration
  5. 2026ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration
  6. 2024Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers
  7. 2026M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts
  8. 2026Bridging Degradation Discrimination and Generation for Universal Image Restoration