mlsanityData to 7 Oct 2026

SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration

arXiv 2603.05940 ↗First posted 6 Mar 2026cs.CVcited by 0

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

Abstract (arXiv)

Image restoration under diverse degradations remains challenging for unified all-in-one frameworks due to feature interference and insufficient expert specialization. We propose SLER-IR, a spherical layer-wise expert routing framework that dynamically activates specialized experts across network layers. To ensure reliable routing, we introduce a Spherical Uniform Degradation Embedding with contrastive learning, which maps degradation representations onto a hypersphere to eliminate geometry bias in linear embedding spaces. In addition, a Global-Local Granularity Fusion (GLGF) module integrates global semantics and local degradation cues to address spatially non-uniform degradations and the train-test granularity gap. Experiments on three-task and five-task benchmarks demonstrate that SLER-IR achieves consistent improvements over state-of-the-art methods in both PSNR and SSIM. Code and models will be publicly released.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 49 of its 65 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

49 of 65 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restoration27 Nov
  2. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration20 Oct
  3. 2023WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal24 Mar

Other references · 46

  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  2. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  3. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  6. 2020Pre-Trained Image Processing Transformercited by 891
  7. 2021Multi-Stage Progressive Image Restorationcited by 813
  8. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  9. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  10. 2022Simple Baselines for Image Restorationcited by 701
  11. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  12. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
34 more
  1. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  2. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  3. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  4. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  5. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  6. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  7. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  8. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  9. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 271
  10. 2020Multi-Scale Progressive Fusion Network for Single Image Derainingcited by 259
  11. 2022Vision Transformers for Single Image Dehazingcited by 255
  12. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  13. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  14. 2019GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazingcited by 227
  15. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  16. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 171
  17. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  18. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  19. 2019Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Trainingcited by 112
  20. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  21. 2020DeepLPF: Deep Local Parametric Filters for Image Enhancementcited by 107
  22. 2024Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restorationcited by 60
  23. 2023Prompt-In-Prompt Learning for Universal Image Restorationcited by 43
  24. 2025Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networkscited by 37
  25. 2024All-In-One Medical Image Restoration via Task-Adaptive Routingcited by 30
  26. 2023Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branchescited by 29
  27. 2024UniProcessor: A Text-induced Unified Low-level Image Processorcited by 22
  28. 2024Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restorationcited by 20
  29. 2024Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restorationcited by 18
  30. 2023Multi-task Image Restoration Guided By Robust DINO Featurescited by 14
  31. 2024Efficient Degradation-aware Any Image Restorationcited by 11
  32. 2023Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Darkcited by 9
  33. 2024Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulationcited by 9
  34. 2024Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restorationcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
  2. 2026Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
  3. 2025M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration
  4. 2026UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
  5. 2025ClusIR: Towards Cluster-Guided All-in-One Image Restoration
  6. 2025RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation
  7. 2025Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration
  8. 2026RIRF: Reasoning Image Restoration Framework