Papers
Topics
Authors
Recent
Search
2000 character limit reached

Conditional Hallucinations for Image Compression

Published 25 Oct 2024 in eess.IV, cs.CV, and cs.LG | (2410.19493v2)

Abstract: In lossy image compression, models face the challenge of either hallucinating details or generating out-of-distribution samples due to the information bottleneck. This implies that at times, introducing hallucinations is necessary to generate in-distribution samples. The optimal level of hallucination varies depending on image content, as humans are sensitive to small changes that alter the semantic meaning. We propose a novel compression method that dynamically balances the degree of hallucination based on content. We collect data and train a model to predict user preferences on hallucinations. By using this prediction to adjust the perceptual weight in the reconstruction loss, we develop a Conditionally Hallucinating compression model (ConHa) that outperforms state-of-the-art image compression methods. Code and images are available at https://polybox.ethz.ch/index.php/s/owS1k5JYs4KD4TA.

Authors (2)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (27)
  1. High-fidelity generative image compression. Advances in Neural Information Processing Systems, 33:11913–11924, 2020.
  2. Po-elic: Perception-oriented efficient learned image coding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1764–1769, 2022.
  3. Gregory K Wallace. The jpeg still picture compression standard. Communications of the ACM, 34(4):30–44, 1991.
  4. Jpeg2000: Standard for interactive imaging. Proceedings of the IEEE, 90(8):1336–1357, 2002.
  5. Google Developers. Webp. https://developers.google.com/speed/webp/. Accessed: May 17, 2024.
  6. Fabrice Bellard. BPG (Better Portable Graphics). https://bellard.org/bpg/. Accessed: May 17, 2024.
  7. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  8. Stochastic backpropagation and approximate inference in deep generative models. In International conference on machine learning, pages 1278–1286. PMLR, 2014.
  9. End-to-end optimized image compression. arXiv preprint arXiv:1611.01704, 2016.
  10. Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436, 2018.
  11. Elic: Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5718–5727, 2022.
  12. Compression.cc. Compression.cc. https://www.compression.cc/. Accessed on May 17, 2024.
  13. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018.
  14. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017.
  15. Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
  16. Real-time adaptive image compression. In International Conference on Machine Learning, pages 2922–2930. PMLR, 2017.
  17. Generative compression. In 2018 Picture Coding Symposium (PCS), pages 258–262. IEEE, 2018.
  18. Deep generative models for distribution-preserving lossy compression. Advances in neural information processing systems, 31, 2018.
  19. Generative adversarial networks for extreme learned image compression. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 221–231, 2019.
  20. Rethinking lossy compression: The rate-distortion-perception tradeoff. In International Conference on Machine Learning, pages 675–685. PMLR, 2019.
  21. Universal rate-distortion-perception representations for lossy compression. Advances in Neural Information Processing Systems, 34:11517–11529, 2021.
  22. Multi-realism image compression with a conditional generator. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22324–22333, 2023.
  23. Controlling rate, distortion, and realism: Towards a single comprehensive neural image compression model. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2900–2909, 2024.
  24. Div2k dataset, 2017. Accessed: 2024-05-22.
  25. TOFlow: Temporal output learning for video frame interpolation. http://toflow.csail.mit.edu/, 2019.
  26. Kodak graphics. http://r0k.us/graphics/kodak/.
  27. Mark E Glickman. A comprehensive guide to chess ratings. American Chess Journal, 3(1):59–102, 1995.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.

HackerNews