mlsanityData to 7 Oct 2026

Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

arXiv 2009.14563 ↗First posted 30 Sep 2020cs.CVcited by 5

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

Abstract (arXiv)

In recent years, deep learning-based methods have been successfully applied to the image distortion restoration tasks. However, scenarios that assume a single distortion only may not be suitable for many real-world applications. To deal with such cases, some studies have proposed sequentially combined distortions datasets. Viewing in a different point of combining, we introduce a spatially-heterogeneous distortion dataset in which multiple corruptions are applied to the different locations of each image. In addition, we also propose a mixture of experts network to effectively restore a multi-distortion image. Motivated by the multi-task learning, we design our network to have multiple paths that learn both common and distortion-specific representations. Our model is effective for restoring real-world distortions and we experimentally verify that our method outperforms other models designed to manage both single distortion and multiple distortions.

Key facts. Cited by 5 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 36 of its 52 references that are in the map. First posted on arXiv 30 Sep 2020.

Builds on

36 of 52 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  11. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  12. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
24 more
  1. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  2. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  3. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  4. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  5. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  6. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  7. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  8. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  9. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  10. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  11. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  12. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 263
  13. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  14. 2019Real Image Denoising with Feature Attentioncited by 176
  15. 2018Image Inpainting via Generative Multi-column Convolutional Neural Networkscited by 81
  16. 2020Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategycited by 66
  17. 2018Crafting a Toolchain for Image Restoration by Deep Reinforcement Learningcited by 45
  18. 2019Path-Restore: Learning Network Path Selection for Image Restorationcited by 39
  19. 2019Learning Implicitly Recurrent CNNs Through Parameter Sharingcited by 27
  20. 2018Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortionscited by 18
  21. 2016Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detectioncited by 10
  22. 2019Suppressing Model Overfitting for Image Super-Resolution Networkscited by 9
  23. 2018Image Distortion Detection using Convolutional Neural Networkcited by 5
  24. 2019Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Networkcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 3.

5 papers.

  1. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 204
  2. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  3. 2025M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restorationcited by 6
  4. 2025Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptationcited by 0
  5. 2025Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2017Quality Resilient Deep Neural Networks
  2. 2024Neural Experts: Mixture of Experts for Implicit Neural Representations
  3. 2023Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
  4. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restoration
  5. 2025Towards Unified Image Deblurring using a Mixture-of-Experts Decoder
  6. 2025RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation
  7. 2026SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration
  8. 2026UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration