mlsanityData to 14 Oct 2026

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

arXiv 2304.03542 ↗First posted 7 Apr 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant. However, the blur involved in real applications are usually space-variant due to object motion, out-of-focus, etc., resulting in severe performance drop of the advanced SR methods. To address this problem, we firstly introduce two new datasets with out-of-focus blur, i.e., NYUv2-BSR and Cityscapes-BSR, to support further researches of blind SR with space-variant blur. Based on the datasets, we design a novel Cross-MOdal fuSion network (CMOS) that estimate both blur and semantics simultaneously, which leads to improved SR results. It involves a feature Grouping Interactive Attention (GIA) module to make the two modalities interact more effectively and avoid inconsistency. GIA can also be used for the interaction of other features because of the universality of its structure. Qualitative and quantitative experiments compared with state-of-the-art methods on above datasets and real-world images demonstrate the superiority of our method, e.g., obtaining PSNR/SSIM by +1.91/+0.0048 on NYUv2-BSR than MANet.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 42 of its 56 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

42 of 56 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  8. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  9. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  12. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
30 more
  1. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  2. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  3. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  4. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 371
  5. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 286
  6. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  7. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  8. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 228
  9. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  10. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  11. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  12. 2015ParseNet: Looking Wider to See Bettercited by 177
  13. 2019Blind Super-Resolution Kernel Estimation using an Internal-GANcited by 175
  14. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  15. 2020Defocus Deblurring Using Dual-Pixel Datacited by 139
  16. 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
  17. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  18. 2020Semantic Flow for Fast and Accurate Scene Parsingcited by 128
  19. 2020Meta-Transfer Learning for Zero-Shot Super-Resolutioncited by 116
  20. 2020Efficient Image Super-Resolution Using Pixel Attentioncited by 87
  21. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  22. 2020Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradationscited by 61
  23. 2021Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutioncited by 52
  24. 2022Deep Constrained Least Squares for Blind Image Super-Resolutioncited by 47
  25. 2020KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustmentcited by 37
  26. 2019Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolverscited by 35
  27. 2022EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithmcited by 27
  28. 2021Analogous to Evolutionary Algorithm: Designing a Unified Sequence Modelcited by 20
  29. 2021EDPN: Enhanced Deep Pyramid Network for Blurry Image Restorationcited by 9
  30. 2019Blind Deblurring using Deep Learning: A Surveycited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6.

7 papers.

  1. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 37
  2. 2023Learning Global-aware Kernel for Image Harmonizationcited by 4
  3. 2024Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolutioncited by 3
  4. 2024Exploring Real&Synthetic Dataset and Linear Attention in Image Restorationcited by 3
  5. 2024Spatially-Variant Degradation Model for Dataset-free Super-resolutioncited by 2
  6. 2024Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolutioncited by 1
  7. 2024DaBiT: Depth and Blur informed Transformer for Video Focal Deblurringcited by 1