mlsanityData to 14 Oct 2026

Memory augment is All You Need for image restoration

arXiv 2309.01377 ↗First posted 4 Sep 2023cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Image restoration is a low-level vision task, most CNN methods are designed as a black box, lacking transparency and internal aesthetics. Although some methods combining traditional optimization algorithms with DNNs have been proposed, they all have some limitations. In this paper, we propose a three-granularity memory layer and contrast learning named MemoryNet, specifically, dividing the samples into positive, negative, and actual three samples for contrastive learning, where the memory layer is able to preserve the deep features of the image and the contrastive learning converges the learned features to balance. Experiments on Derain/Deshadow/Deblur task demonstrate that these methods are effective in improving restoration performance. In addition, this paper's model obtains significant PSNR, SSIM gain on three datasets with different degradation types, which is a strong proof that the recovered images are perceptually realistic. The source code of MemoryNet can be obtained from https://github.com/zhangbaijin/MemoryNet

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 41 of its 66 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

41 of 66 references.

References · 41

  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  2. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  3. 2021Multi-Stage Progressive Image Restorationcited by 816
  4. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  5. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  6. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 352
  7. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 312
  8. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 302
  9. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  10. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 272
  11. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  12. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
29 more
  1. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 213
  2. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  3. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  4. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 163
  5. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
  6. 2022Deep Generalized Unfolding Networks for Image Restorationcited by 121
  7. 2019Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Trainingcited by 112
  8. 2019Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANcited by 103
  9. 2019Shadow Removal via Shadow Image Decompositioncited by 98
  10. 2019Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Datacited by 92
  11. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 79
  12. 2022DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Networkcited by 69
  13. 2018Direction-aware Spatial Context Features for Shadow Detection and Removalcited by 58
  14. 2021From Shadow Generation to Shadow Removalcited by 55
  15. 2021CANet: A Context-Aware Network for Shadow Removalcited by 47
  16. 2020Shadow Removal by a Lightness-Guided Network with Training on Unpaired Datacited by 38
  17. 2019RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removalcited by 35
  18. 2018Non-locally Enhanced Encoder-Decoder Network for Single Image De-rainingcited by 33
  19. 2020Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Networkcited by 29
  20. 2020Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentationcited by 26
  21. 2021Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removalcited by 24
  22. 2020Low-light Image Restoration with Short- and Long-exposure Raw Pairscited by 18
  23. 2020SiENet: Siamese Expansion Network for Image Extrapolationcited by 18
  24. 2021COLA-Net: Collaborative Attention Network for Image Restorationcited by 16
  25. 2022SpA-Former: Transformer image shadow detection and removal via spatial attentioncited by 7
  26. 2020Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Networkcited by 5
  27. 2020Self-Supervised Shadow Removalcited by 5
  28. 2021Memory Regulation and Alignment toward Generalizer RGB-Infrared Personcited by 2
  29. 2022Compound Multi-branch Feature Fusion for Real Image Restorationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 1.

8 papers.

  1. 2024Diffusion Enhancement for Cloud Removal in Ultra-Resolution Remote Sensing Imagerycited by 16
  2. 2024High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformercited by 12
  3. 2025Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design Spacecited by 12
  4. 2024Test-Time Intensity Consistency Adaptation for Shadow Detectioncited by 11
  5. 2025DC4CR: When Cloud Removal Meets Diffusion Control in Remote Sensingcited by 4
  6. 2024Adaptive Query Prompting for Multi-Domain Landmark Detectioncited by 0
  7. 2025Image Restoration via Multi-domain Learningcited by 0
  8. 2026ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removalcited by 0