Papers
Topics
Authors
Recent
Search
2000 character limit reached

Traditional Transformation Theory Guided Model for Learned Image Compression

Published 24 Feb 2024 in eess.IV and cs.CV | (2402.15744v1)

Abstract: Recently, many deep image compression methods have been proposed and achieved remarkable performance. However, these methods are dedicated to optimizing the compression performance and speed at medium and high bitrates, while research on ultra low bitrates is limited. In this work, we propose a ultra low bitrates enhanced invertible encoding network guided by traditional transformation theory, experiments show that our codec outperforms existing methods in both compression and reconstruction performance. Specifically, we introduce the Block Discrete Cosine Transformation to model the sparsity of features and employ traditional Haar transformation to improve the reconstruction performance of the model without increasing the bitstream cost.

Authors (3)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. G. K. Wallace, “The jpeg still picture compression standard,” IEEE Transactions on Consumer Electronics, vol. 38, no. 1, p. xviii–xxxiv, 1992.
  2. D. S. Taubman and M. W. Marcellin, “Jpeg2000: Image compression fundamentals, standards and practice,” Journal of Electronic Imaging, vol. 11, no. 2, pp. 286–287, 2002.
  3. Google, “Web picture format,” 2022.
  4. B. Fabrice, “BPG image format.” 2018, https://bellard.org/bpg.
  5. G. Toderici, S. O’Malley, S. J. Hwang, D. Vincent, D. Minnen, S. Baluja, M. Covell, and R. Sukthankar, “Variable rate image compression with recurrent neural networks,” International Conference on Learning Representations, 2016.
  6. D. Minnen, J. Ballé, and G. Toderici, “Joint autoregressive and hierarchical priors for learned image compression,” 2018, in: Proceedings of the Neural Information Processing Systems. pp(10794-10803).
  7. Z. Cheng, H. Sun, M. Takeuchi, and J. Katto, “Learned image compression with discretized gaussian mixture likelihoods and attention modules,” 2020, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp(7939–7948). https://doi.org/10.1109/cvpr42600.2020.00796.
  8. E. Agustsson, M. Tschannen, F. Mentzer, R. Timofte, and L. V. Gool, “Generative adversarial networks for extreme learned image compression,” 2019, in: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp(221-231).
  9. Y. Xie, K. L. Cheng, and Q. Chen, “Enhanced invertible encoding for learned image compression,” 2021, In: Proceedings of the 29th ACM International Conference on Multimedia. https://doi.org/10.1145/3474085.3475213.
  10. E. K. Company, “Kodak lossless true color image suite,” 2013, http://r0k.us/graphics/kodak.
  11. J. V. E. T. (JVET), “Vvc official test model vtm.” 2021.
  12. G. Toderici, D. Vincent, N. Johnston, S. J. Hwang, D. Minnen, J. Shor, and M. Covell, “Full resolution image compression with recurrent neural networks,” 2017, in: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. pp(5306-5314). https://arxiv.org/abs/1608.05148.
  13. N. Johnston, D. Vincent, D. Minnen, M. Covell, S. Singh, T. Chinen, S. J. Hwang, J. Shor, and G. Toderici, “Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks,” 2018, in: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. pp(4385-4393).
  14. Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, p. 600–612, 2004.
  15. H. Zhao, O. Gallo, I. Frosio, and J. Kautz, “Loss functions for image restoration with neural networks,” IEEE Transactions on Computational Imaging, vol. 3, no. 1, p. 47–57, 2016.
  16. J. Ballé, V. Laparra, and E. P. Simoncelli, “End-to-end optimized image compression,” 2017, in: Proceedings of the International Conference on Learning Representations. pp(1-12).
  17. Z. Guo, Y. Wu, R. Feng, Z. Zhang, and Z. Chen, “3-d context entropy model for improved practical image compression,” 2020, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp(116–117).
  18. D. Minnen and S. Singh, “Channel-wise autoregressive entropy models for learned image compression,” 2020, in: Proceedings of the IEEE International Conference on Image Processing. pp(3339–3343). https://doi.org/10.1109/icip40778.2020.9190935.
  19. Y. Hu, W. Yang, and J. Liu, “Coarse-to-fine hyper-prior modeling for learned image compression,” 2020, in: Proceedings of the AAAI Conference on Artificial Intelligence. pp(11013–11020). https://doi.org/10.1609/aaai.v34i07.6736.
  20. J. Balle, V. Laparra, and E. Simoncelli, “End-to-end optimization of nonlinear transform codes for perceptual quality,” 2016, in: Proceedings of Picture Coding Symposium. pp(1-5). https://doi.org/10.1109/pcs.2016.7906310.
  21. T. Chen, H. Liu, Z. Ma, Q. Shen, X. Cao, and Y. Wang, “End-to-end learnt image compression via non-local attention optimization and improved context modeling,” IEEE Transactions on Image Processing, vol. 30, no. 1, p. 3179–3191, 2021.
  22. Y. Zhang, K. Li, K. Li, B. Zhong, and Y. Fu, “Residual non-local attention networks for image restoration,” 2019, in: Proceedings of the International Conference on Learning Representations. pp(1–13).
  23. L. Zhou, Z. Sun, X. Wu, J. Wu, and Y. Fu, “End-to-end optimized image compression with attention mechanism,” 2019, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp(1–4).
  24. O. Rippel and L. Bourdev, “Real-time adaptive image compression,” 2017, in: Proceedings of the International Conference on Machine Learning. pp(2922–2930).
  25. L. Dinh, J. Sohl-Dickstein, and S. Bengio, “Density estimation using real nvp,” 2017, in: Proceedings of the International Conference on Learning Representations. pp(1–10).
  26. D. P. Kingma and P. Dhariwal, “Glow: Generative flow with invertible 1x1 convolutions. neural information processing systems,” 2018, in: Proceedings of the Neural Information Processing Systems. pp(1–10).
  27. J. Ballé, D. Minnen, S. Singh, S. Hwang, and N. Johnston, “Variational image compression with a scale hyperprior,” 2018, in: Proceedings of the International Conference on Learning Representations. pp(1–13).
  28. P. I. Wilson and J. Fernandez, “Facial feature detection using haar classifiers,” Journal of Computing Sciences in Colleges, vol. 21, no. 4, p. 127–133, 2006.
  29. R. Lienhart and J. Maydt, “An extended set of haar-like features for rapid object detection,” 2002, proceedings of the International Conference on Image Processing. pp(900–903).
  30. L. Ardizzone, C. Lüth, J. Kruse, C. Rother, and U. Köthe, “Guided image generation with conditional invertible neural networks,” 2019, https://arxiv.org/abs/1907.02392.
  31. J. Duda, “Asymmetric numeral systems,” 2009, https://arxiv.org/abs/0902.0271.
  32. Z. Wang, E. P. Simoncelli, and A. C. Bovik, “Multiscale structural similarity for image quality assessment,” 2003, in: Proceedings of the Asilomar Conference on Signals, Systems and Computers. pp(1398-1402).
  33. J. Bégaint, F. Racapé, S. Feltman, and A. Pushparaja, “Compressai: a pytorch library and evaluation platform for end-to-end compression research,” 2020, https://arxiv.org/abs/2011.03029.
  34. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2015, in: Proceedings of the International Conference on Learning Representations. pp(1-11).

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

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

Sign Up to Generate

Open Problems

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

Generate Now

Continue Learning

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

Generate Now

Collections

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

Sign Up