Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the Importance of Denoising when Learning to Compress Images (2307.06233v1)

Published 12 Jul 2023 in eess.IV and cs.CV

Abstract: Image noise is ubiquitous in photography. However, image noise is not compressible nor desirable, thus attempting to convey the noise in compressed image bitstreams yields sub-par results in both rate and distortion. We propose to explicitly learn the image denoising task when training a codec. Therefore, we leverage the Natural Image Noise Dataset, which offers a wide variety of scenes captured with various ISO numbers, leading to different noise levels, including insignificant ones. Given this training set, we supervise the codec with noisy-clean image pairs, and show that a single model trained based on a mixture of images with variable noise levels appears to yield best-in-class results with both noisy and clean images, achieving better rate-distortion than a compression-only model or even than a pair of denoising-then-compression models with almost one order of magnitude fewer GMac operations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (24)
  1. Featured pictures on wikimedia commons. https://commons.wikimedia.org/wiki/Category:Featured_pictures_on_Wikimedia_Commons. Accessed: 2020-04-03.
  2. Challenge on learned image compression. http://clic.compression.cc/2021/tasks, 2020.
  3. A high-quality denoising dataset for smartphone cameras. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1692–1700, June 2018.
  4. Johannes Ballé. Efficient nonlinear transforms for lossy image compression. In 2018 Picture Coding Symposium (PCS), 2018.
  5. End-to-end optimized image compression. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 2017.
  6. Variational image compression with a scale hyperprior. In International Conference on Learning Representations, 2018.
  7. The perception-distortion tradeoff. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
  8. Benoit Brummer and Christophe De Vleeschouwer. Natural image noise dataset. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 1777–1784, June 2019.
  9. Benoit Brummer and Christophe De Vleeschouwer. End-to-end optimized image compression with competition of prior distributions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 1890–1894, June 2021.
  10. Combined image compression and denoising using wavelets. Image Commun., 22(1):86–101, jan 2007.
  11. A non-local algorithm for image denoising. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 2, pages 60–65 vol. 2, June 2005.
  12. Toward interactive modulation for photo-realistic image restoration. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 294–303, 2021.
  13. Image denoising via lossy compression and wavelet thresholding. In Proceedings of International Conference on Image Processing, volume 1, pages 604–607 vol.1, 1997.
  14. Learning to see in the dark. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3291–3300, 06 2018.
  15. Image denoising with block-matching and 3d filtering. Proceedings of SPIE - The International Society for Optical Engineering, 6064:354–365, 02 2006.
  16. Distilling the knowledge in a neural network. In NIPS Deep Learning and Representation Learning Workshop, 2015.
  17. Mark A. Kramer. Nonlinear principal component analysis using autoassociative neural networks. AIChE Journal, 37(2):233–243, 1991.
  18. Cross-patch graph convolutional network for image denoising. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4651–4660, October 2021.
  19. Modeling and estimation of signal-dependent noise in hyperspectral imagery. Appl. Opt., 50(21):3829–3846, Jul 2011.
  20. Benchmarking denoising algorithms with real photographs. In 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR), pages 2750–2759, 2017.
  21. U-net: Convolutional networks for biomedical image segmentation. In Nassir Navab, Joachim Hornegger, William M. Wells, and Alejandro F. Frangi, editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham, 2015. Springer International Publishing.
  22. Image denoising using wavelet transform. In 2010 International Conference on Mechanical and Electrical Technology, pages 509–515, 09 2010.
  23. Towards image denoising in the latent space of learning-based compression. In Andrew G. Tescher and Touradj Ebrahimi, editors, Applications of Digital Image Processing XLIV, volume 11842, pages 412 – 422. International Society for Optics and Photonics, SPIE, 2021.
  24. Multiscale structural similarity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems Computers, 2003, volume 2, pages 1398–1402 Vol.2, Nov 2003.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
Citations (4)
View on Semantic Scholar

Summary

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

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