Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning the Degradation Distribution for Blind Image Super-Resolution (2203.04962v2)

Published 9 Mar 2022 in eess.IV and cs.CV

Abstract: Synthetic high-resolution (HR) & low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degrading) process via a deterministic model. However, some degradations in real scenarios are stochastic and cannot be determined by the content of the image. These deterministic models may fail to model the random factors and content-independent parts of degradations, which will limit the performance of the following SR models. In this paper, we propose a probabilistic degradation model (PDM), which studies the degradation $\mathbf{D}$ as a random variable, and learns its distribution by modeling the mapping from a priori random variable $\mathbf{z}$ to $\mathbf{D}$. Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones. Extensive experiments have demonstrated that our degradation model can help the SR model achieve better performance on different datasets. The source codes are released at \url{[email protected]:greatlog/UnpairedSR.git}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Blind super-resolution kernel estimation using an internal-gan. In NeurIPS, 2019.
  2. Ludwig Boltzmann. Studien uber das gleichgewicht der lebenden kraft. Wissenschafiliche Abhandlungen, 1:49–96, 1868.
  3. Unprocessing images for learned raw denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11036–11045, 2019.
  4. To learn image super-resolution, use a gan to learn how to do image degradation first. In ECCV, 2018.
  5. Learning to generate realistic noisy images via pixel-level noise-aware adversarial training. In Advances in Neural Information Processing Systems, 2021.
  6. Mask-guided spectral-wise transformer for efficient hyperspectral image reconstruction. arXiv e-prints, pages arXiv–2111, 2021.
  7. Unsupervised image super-resolution with an indirect supervised path. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 468–469, 2020.
  8. Rformer: Transformer-based generative adversarial network for real fundus image restoration on a new clinical benchmark. arXiv e-prints, pages arXiv–2201, 2022.
  9. Learning a deep convolutional network for image super-resolution. In European Conference on Computer Vision, pages 184–199. Springer, 2014.
  10. Accelerating the super-resolution convolutional neural network. In European conference on computer vision, pages 391–407. Springer, 2016.
  11. Frequency separation for real-world super-resolution. In 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pages 3599–3608. IEEE, 2019.
  12. Generative adversarial nets. Advances in Neural Information Processing Systems, 27, 2014.
  13. Blind super-resolution with iterative kernel correction. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1604–1613, 2019.
  14. Samuel W. Hasinoff. Photon, poisson noise. In Computer Vision, A Reference Guide, 2014.
  15. Real-world super-resolution via kernel estimation and noise injection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 466–467, 2020.
  16. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  17. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25:1097–1105, 2012.
  18. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4681–4690, 2017.
  19. Dfan: Dual feature aggregation network for lightweight image super-resolution. Wireless Communications and Mobile Computing, 2022, 2022.
  20. Approaching the limit of image rescaling via flow guidance. arXiv preprint arXiv:2111.05133, 2021.
  21. From general to specific: Online updating for blind super-resolution. Pattern Recognition, page 108613, 2022.
  22. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 136–144, 2017.
  23. Flow-guided sparse transformer for video deblurring. arXiv preprint arXiv:2201.01893, 2022.
  24. Blind image super-resolution: A survey and beyond. arXiv preprint arXiv:2107.03055, 2021.
  25. Ntire 2020 challenge on real-world image super-resolution: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 494–495, 2020.
  26. Unfolding the alternating optimization for blind super resolution. Advances in Neural Information Processing Systems (NeurIPS), 33, 2020.
  27. Efficient super resolution by recursive aggregation. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 8592–8599. IEEE, 2021.
  28. End-to-end alternating optimization for blind super resolution. ArXiv, abs/2105.06878, 2021.
  29. Shunta Maeda. Unpaired image super-resolution using pseudo-supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 291–300, 2020.
  30. Making a “completely blind” image quality analyzer. IEEE Signal Processing Letters, 20(3):209–212, 2012.
  31. Benchmarking denoising algorithms with real photographs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1586–1595, 2017.
  32. Jpeg-resistant adversarial images. In NIPS 2017 Workshop on Machine Learning and Computer Security, volume 1, 2017.
  33. Ntire 2017 challenge on single image super-resolution: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 114–125, 2017.
  34. Ntire 2018 challenge on single image super-resolution: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 852–863, 2018.
  35. Deep generative adversarial residual convolutional networks for real-world super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 438–439, 2020.
  36. Real-esrgan: Training real-world blind super-resolution with pure synthetic data. arXiv preprint arXiv:2107.10833, 2021.
  37. Esrgan: Enhanced super-resolution generative adversarial networks. ArXiv, abs/1809.00219, 2018.
  38. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612, 2004.
  39. Unsupervised real-world image super resolution via domain-distance aware training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13385–13394, 2021.
  40. Deep unfolding network for image super-resolution. ArXiv, abs/2003.10428, 2020.
  41. Designing a practical degradation model for deep blind image super-resolution. arXiv preprint arXiv:2103.14006, 2021.
  42. Learning a single convolutional super-resolution network for multiple degradations. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3262–3271, 2018.
  43. Deep plug-and-play super-resolution for arbitrary blur kernels. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1671–1681, 2019.
  44. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
  45. Image super-resolution using very deep residual channel attention networks. In Proceedings of the European Conference on Computer Vision (ECCV), pages 286–301, 2018.
  46. Residual dense network for image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2472–2481, 2018.
  47. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision, pages 2223–2232, 2017.
Citations (50)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now