mlsanityData to 14 Oct 2026

Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration

arXiv 2407.19139 ↗First posted 27 Jul 2024cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

The use of a single image restoration framework to achieve multi-task image restoration has garnered significant attention from researchers. However, several practical challenges remain, including meeting the specific and simultaneous demands of different tasks, balancing relationships between tasks, and effectively utilizing task correlations in model design. To address these challenges, this paper explores a multi-expert adaptive selection mechanism. We begin by designing a feature representation method that accounts for both the pixel channel level and the global level, encompassing low-frequency and high-frequency components of the image. Based on this method, we construct a multi-expert selection and ensemble scheme. This scheme adaptively selects the most suitable expert from the expert library according to the content of the input image and the prompts of the current task. It not only meets the individualized needs of different tasks but also achieves balance and optimization across tasks. By sharing experts, our design promotes interconnections between different tasks, thereby enhancing overall performance and resource utilization. Additionally, the multi-expert mechanism effectively eliminates irrelevant experts, reducing interference from them and further improving the effectiveness and accuracy of image restoration. Experimental results demonstrate that our proposed method is both effective and superior to existing approaches, highlighting its potential for practical applications in multi-task image restoration.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 53 of its 98 references that are in the map. First posted on arXiv 27 Jul 2024.

Builds on

53 of 98 references.

References · 53

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  6. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  8. 2020Pre-Trained Image Processing Transformercited by 893
  9. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  10. 2021Multi-Stage Progressive Image Restorationcited by 816
  11. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  12. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
38 more
  1. 2022Simple Baselines for Image Restorationcited by 708
  2. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  3. 2017Benchmarking Single Image Dehazing and Beyondcited by 447
  4. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  5. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  6. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  7. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 272
  8. 2020Multi-Scale Progressive Fusion Network for Single Image Derainingcited by 260
  9. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 244
  10. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 237
  11. 2024A Survey on Mixture of Experts in Large Language Modelscited by 237
  12. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  13. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  14. 2020Deblurring by Realistic Blurringcited by 188
  15. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  16. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  17. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  18. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 140
  19. 2022Deep Generalized Unfolding Networks for Image Restorationcited by 121
  20. 2019Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Rainingcited by 117
  21. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 111
  22. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 110
  23. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 100
  24. 2020FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazingcited by 80
  25. 2023ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restorationcited by 77
  26. 2019A General Decoupled Learning Framework for Parameterized Image Operatorscited by 72
  27. 2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 55
  28. 2024Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategycited by 50
  29. 2023Prompt-In-Prompt Learning for Universal Image Restorationcited by 43
  30. 2023Language-driven All-in-one Adverse Weather Removalcited by 36
  31. 2023Improving Image Restoration through Removing Degradations in Textual Representationscited by 36
  32. 2024Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazingcited by 32
  33. 2021MC-Blur: A Comprehensive Benchmark for Image Deblurringcited by 27
  34. 2021Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removalcited by 24
  35. 2021Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Priorcited by 18
  36. 2023Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removalcited by 12
  37. 2023Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removalcited by 12
  38. 2022Multi-scale Attentive Image De-raining Networks via Neural Architecture Searchcited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 9.

18 papers.

Sort:

By area:

  1. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restorationcited by 77
  2. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 60
  3. 2025M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restorationcited by 7
  4. 2024Learning Efficient and Effective Trajectories for Differential Equation-based Image Restorationcited by 5
  5. 2025ClusIR: Towards Cluster-Guided All-in-One Image Restorationcited by 5
  6. 2025PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restorationcited by 4
  7. 2025Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinementcited by 3
  8. 2025DFDNet: Dynamic Frequency-Guided De-Flare Networkcited by 2
  9. 2026CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restorationcited by 2
  10. 2025Wavelet-Enhanced Desnowing: A Novel Single Image Restoration Approach for Traffic Surveillance under Adverse Weather Conditionscited by 0
  11. 2026Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priorscited by 0
  12. 2026SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restorationcited by 0
6 more
  1. 2026M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Expertscited by 0
  2. 2026Unified Restoration-Perception Learning: Maritime Infrared-Visible Image Fusion and Segmentationcited by 0
  3. 2026Divide and Restore: A Modular Task-Decoupled Framework for Universal Image Restorationcited by 0
  4. 2026QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibrationcited by 0
  5. 2026What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restorationcited by 0
  6. 2026Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidancecited by 0