mlsanityData to 7 Oct 2026

Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images

arXiv 2302.12491 ↗First posted 24 Feb 2023cs.CV cs.AI eess.IVcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper proposes crack segmentation augmented by super resolution (SR) with deep neural networks. In the proposed method, a SR network is jointly trained with a binary segmentation network in an end-to-end manner. This joint learning allows the SR network to be optimized for improving segmentation results. For realistic scenarios, the SR network is extended from non-blind to blind for processing a low-resolution image degraded by unknown blurs. The joint network is improved by our proposed two extra paths that further encourage the mutual optimization between SR and segmentation. Comparative experiments with State of The Art (SoTA) segmentation methods demonstrate the superiority of our joint learning, and various ablation studies prove the effects of our contributions.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 60 of its 130 references that are in the map. First posted on arXiv 24 Feb 2023.

Builds on

60 of 130 references.

References · 60

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017Mask R-CNNcited by 7,259
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2018Panoptic Segmentationcited by 796
  11. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  12. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
38 more
  1. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  2. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  3. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  4. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  5. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  6. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  7. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  8. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
  9. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  10. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  11. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  12. 2018Boundary loss for highly unbalanced segmentationcited by 187
  13. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  14. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  15. 2019Feedback Network for Image Super-Resolutioncited by 155
  16. 2019Recurrent Back-Projection Network for Video Super-Resolutioncited by 147
  17. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  18. 2019Image Super-Resolution by Neural Texture Transfercited by 119
  19. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  20. 2020Meta-Transfer Learning for Zero-Shot Super-Resolutioncited by 116
  21. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  22. 2020Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolutioncited by 90
  23. 2021Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationcited by 88
  24. 2019Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detectioncited by 80
  25. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 79
  26. 2017Perceptual Generative Adversarial Networks for Small Object Detectioncited by 76
  27. 2018Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentationcited by 76
  28. 2016Finding Tiny Facescited by 72
  29. 2017Class Rectification Hard Mining for Imbalanced Deep Learningcited by 67
  30. 2018Task-Driven Super Resolution: Object Detection in Low-resolution Imagescited by 52
  31. 2020Space-Time-Aware Multi-Resolution Video Enhancementcited by 48
  32. 2020Fast Adaptation to Super-Resolution Networks via Meta-Learningcited by 46
  33. 2021Learning to Resize Images for Computer Vision Taskscited by 45
  34. 2019Explorable Super Resolutioncited by 44
  35. 2020KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustmentcited by 37
  36. 2019Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolverscited by 35
  37. 2021Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentationcited by 34
  38. 2021PointFlow: Flowing Semantics Through Points for Aerial Image Segmentationcited by 29

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 3.

7 papers.

  1. 2023Fine-tuning vision foundation model for crack segmentation in civil infrastructurescited by 14
  2. 2024Inpainting-Driven Mask Optimization for Object Removalcited by 1
  3. 2025Semantic-Guided Global-Local Collaborative Networks for Lightweight Image Super-Resolutioncited by 1
  4. 2024NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTIcited by 0
  5. 2024Depth Estimation fusing Image and Radar Measurements with Uncertain Directionscited by 0
  6. 2025Iterative Optimal Attention and Local Model for Single Image Rain Streak Removalcited by 0
  7. 2025Efficient Cost-and-Quality Controllable Arbitrary-scale Super-resolution with Fourier Constraintscited by 0