mlsanityData to 7 Oct 2026

FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration

arXiv 2511.14099 ↗First posted 18 Nov 2025cs.CV cs.AIcited by 3

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

All-in-One Image Restoration (AIO-IR) aims to develop a unified model that can handle multiple degradations under complex conditions. However, existing methods often rely on task-specific designs or latent routing strategies, making it hard to adapt to real-world scenarios with various degradations. We propose FAPE-IR, a Frequency-Aware Planning and Execution framework for image restoration. It uses a frozen Multimodal Large Language Model (MLLM) as a planner to analyze degraded images and generate concise, frequency-aware restoration plans. These plans guide a LoRA-based Mixture-of-Experts (LoRA-MoE) module within a diffusion-based executor, which dynamically selects high- or low-frequency experts, complemented by frequency features of the input image. To further improve restoration quality and reduce artifacts, we introduce adversarial training and a frequency regularization loss. By coupling semantic planning with frequency-based restoration, FAPE-IR offers a unified and interpretable solution for all-in-one image restoration. Extensive experiments show that FAPE-IR achieves state-of-the-art performance across seven restoration tasks and exhibits strong zero-shot generalization under mixed degradations.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 76 of its 119 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

76 of 119 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration9 Jun
  2. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restoration27 Nov

Other references · 74

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  8. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  9. 2017Deep Image Priorcited by 1,097
  10. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  11. 2022Denoising Diffusion Restoration Modelscited by 951
  12. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
38 more
  1. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  2. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  3. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  4. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  5. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  6. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  7. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  8. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  9. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  10. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  11. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  12. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 363
  13. 2017Compressed Sensing using Generative Modelscited by 337
  14. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  15. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  16. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  17. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  18. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  19. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 241
  20. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  21. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  22. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  23. 2019Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolutioncited by 140
  24. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  25. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 129
  26. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  27. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  28. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  29. 2025Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decodingcited by 101
  30. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  31. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understandingcited by 81
  32. 2023ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restorationcited by 77
  33. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  34. 2023Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restorationcited by 50
  35. 2025Unified Multimodal Discrete Diffusioncited by 46
  36. 2023Prompt-In-Prompt Learning for Universal Image Restorationcited by 43
  37. 2025UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Priorcited by 39
  38. 2025Degradation-Aware Feature Perturbation for All-in-One Image Restorationcited by 39

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026SwiftVR: Real-Time One-Step Generative Video Restorationcited by 2
  2. 2026PixRestore: Unified Image Restoration via Pixel Diffusion Transformercited by 2
  3. 2026LensBridge: Frequency-Guided Compound Degradation Adaptation for Lens Aberration Correction and Veiling Glare Removalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration
  2. 2026Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
  3. 2025ClusIR: Towards Cluster-Guided All-in-One Image Restoration
  4. 2026ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration
  5. 2024Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers
  6. 2026UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
  7. 2026Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
  8. 2025Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback