mlsanityData to 14 Oct 2026

Versatile Cataract Fundus Image Restoration Model Utilizing Unpaired Cataract and High-quality Images

arXiv 2411.12278 ↗First posted 19 Nov 2024eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Cataract is one of the most common blinding eye diseases and can be treated by surgery. However, because cataract patients may also suffer from other blinding eye diseases, ophthalmologists must diagnose them before surgery. The cloudy lens of cataract patients forms a hazy degeneration in the fundus images, making it challenging to observe the patient's fundus vessels, which brings difficulties to the diagnosis process. To address this issue, this paper establishes a new cataract image restoration method named Catintell. It contains a cataract image synthesizing model, Catintell-Syn, and a restoration model, Catintell-Res. Catintell-Syn uses GAN architecture with fully unsupervised data to generate paired cataract-like images with realistic style and texture rather than the conventional Gaussian degradation algorithm. Meanwhile, Catintell-Res is an image restoration network that can improve the quality of real cataract fundus images using the knowledge learned from synthetic cataract images. Extensive experiments show that Catintell-Res outperforms other cataract image restoration methods in PSNR with 39.03 and SSIM with 0.9476. Furthermore, the universal restoration ability that Catintell-Res gained from unpaired cataract images can process cataract images from various datasets. We hope the models can help ophthalmologists identify other blinding eye diseases of cataract patients and inspire more medical image restoration methods in the future.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 48 references that are in the map. First posted on arXiv 19 Nov 2024.

Builds on

20 of 48 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2022A ConvNet for the 2020scited by 3,579
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  8. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  9. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  10. 2020Deblurring by Realistic Blurringcited by 188
  11. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  12. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
8 more
  1. 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
  2. 2018Gated Context Aggregation Network for Image Dehazing and Derainingcited by 89
  3. 2019Evaluation of Retinal Image Quality Assessment Networks in Different Color-spacescited by 57
  4. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  5. 2022An Annotation-free Restoration Network for Cataractous Fundus Imagescited by 20
  6. 2024Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wildcited by 13
  7. 2018Structure-preserving Guided Retinal Image Filtering and Its Application for Optic Disc Analysiscited by 12
  8. 2023A Generic Fundus Image Enhancement Network Boosted by Frequency Self-supervised Representation Learningcited by 10

Built on by

Not cited yet.