Abstract
This paper considers lossless image compression and presents a learned compression system that can achieve state-of-the-art lossless compression performance but uses only 59K parameters, which is one or two order of magnitudes less than other learned systems proposed recently in the literature. The explored system is based on a learned pixel-by-pixel lossless image compression method, where each pixel’s probability distribution parameters are obtained by processing the pixel’s causal neighborhood (i.e. previously encoded/decoded pixels) with a simple neural network comprising 59K parameters. This causality causes the decoder to operate sequentially, i.e. the neural network has to be evaluated for each pixel sequentially, which increases decoding time significantly with common GPU software and hardware. To reduce the decoding time, parallel decoding algorithms are proposed and implemented. The obtained lossless image compression system is compared to traditional and learned systems in the literature in terms of compression performance, encoding-decoding times and computational complexity.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data Availability
The datasets analysed during the current study (for both training and testing) are available from a third party on GitHub https://github.com/fab-jul/L3C-PyTorch.
Code Availability
The codes to repeat the results in this paper are available from the authors on GitHub https://github.com/ssgms/A-Learned-Pixel-by-Pixel-Lossless-Image-Compression-Method-with-59K-Parameters-and-Par-allel-Decoding
Notes
Here, we follow the convention in the related previous research and use sub-pixel to denote each color component and pixel to denote all color components together
References
Boutell, T. & Lane, T. Png (portable network graphics) specification version 1.0. Network Working Group 1–102 (1997)
Cao, S., Wu, C.-Y. & Krähenbühl, P. Lossless image compression through super-resolution. ar**v preprint http://arxiv.org/abs/2004.02872ar**v:2004.02872 (2020)
Chi CC et al (2012) Parallel scalability and efficiency of hevc parallelization approaches. IEEE Transactions on circuits and systems for video technology 22(12):1827–1838
Chrabaszcz, P., Loshchilov, I. & Hutter, F. A downsampled variant of imagenet as an alternative to the cifar datasets. ar**v preprint http://arxiv.org/abs/1707.08819ar**v:1707.08819 (2017)
Christopoulos C, Skodras A, Ebrahimi T (2000) The jpeg2000 still image coding system: an overview. IEEE transactions on consumer electronics 46(4):1103–1127
Fu, C. Numpyac: Fast autoregressive arithmetic coding. https://github.com/zb12138/NumpyAc (2022). Last accessed 2 February 2022
Google. An image format for the web. https://developers.google.com/speed/webp (2022). Last accessed 12 October 2022
Gumus, S. & Kamisli, F. A learned pixel-by-pixel lossless image compression method with 59k parameters and parallel decoding. https://github.com/ssgms/A-Learned-Pixel-by-Pixel-Lossless-Image-Compression-Method-with-59K-Parameters-and-Parallel-Decoding (2022). Last accessed November 2022
Hoogeboom, E., Peters, J. W., van den Berg, R. & Welling, M. Integer discrete flows and lossless compression (2019)
Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. ar**v preprint http://arxiv.org/abs/1412.6980ar**v:1412.6980 (2014)
Krasin, I. et al. Openimages: A public dataset for large-scale multi-label and multi-class image classification. Dataset available from https://github.com/openimages2 (3), 18 (2017)
Lee, Y.-L., Han, K.-H. & Sullivan, G. J. Improved lossless intra coding for h. 264/mpeg-4 avc. IEEE Transactions on Image Processing 15 (9), 2610–2615 (2006)
Liu X, An P, Chen Y, Huang X (2022) An improved lossless image compression algorithm based on huffman coding. Multimedia Tools and Applications 81(4):4781–4795
Malvar, H. & Sullivan, G. Ycocg-r: A color space with rgb reversibility and low dynamic range. ISO/IEC JTC1/SC29/WG11 and ITU-T SG16 Q 6 (2003)
Marpe, D., Schwarz, H. & Wiegand, T. Context-based adaptive binary arithmetic coding in the h. 264/avc video compression standard. IEEE Transactions on circuits and systems for video technology 13 (7), 620–636 (2003)
Masmoudi A, Puech W, Masmoudi A (2015) An improved lossless image compression based arithmetic coding using mixture of non-parametric distributions. Multimedia Tools and Applications 74(23):10605–10619
Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R. & Van Gool, L. Practical full resolution learned lossless image compression (2019)
Mentzer, F. Practical full resolution learned lossless image compression. https://github.com/fab-jul/L3C-PyTorch. Last accessed 29 April 2023
Paszke, A. et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)
Pennebaker, W. B. & Mitchell, J. L. JPEG: Still image data compression standard (Springer Science & Business Media, 1992)
Reed, S. et al. Parallel multiscale autoregressive density estimation (2017)
Ryder, T., Zhang, C., Kang, N. & Zhang, S. Split hierarchical variational compression (2022)
Salimans, T., Karpathy, A., Chen, X. & Kingma, D. P. PixelCNN++: Improving the pixelCNN with discretized logistic mixture likelihood and other modifications (2017). https://openreview.net/forum?id=BJrFC6ceg
Sneyers J (2016) & Wuille, P. Free lossless image format based on maniac compression, Flif
Sovrasov, V. Flops counter for convolutional networks in pytorch framework. https://github.com/sovrasov/flops-counter.pytorch (2022). Last accessed November 2022
Van den Oord, A. et al. Conditional image generation with pixelcnn decoders. Advances in neural information processing systems 29 (2016)
Van Oord, A., Kalchbrenner, N. & Kavukcuoglu, K. Pixel recurrent neural networks (2016)
van den Berg, R., A. Gritsenko, A., Dehghani, M., Kaaeønderby, C. & Salimans, T. Idf\(+\): Analyzing and improving integer discrete flows for lossless compression (2021)
Weinberger MJ, Seroussi G, Sapiro G (2000) The loco-i lossless image compression algorithm: Principles and standardization into jpeg-ls. IEEE Transactions on Image processing 9(8):1309–1324
Zhang, H. et al. Lossless image compression using a multi-scale progressive statistical model (2020)
Zhang S, Kang N, Ryder T, Li Z (2021) iflow: Numerically invertible flows for efficient lossless compression via a uniform coder. Advances in Neural Information Processing Systems 34:5822–5833
Zhang, M., Townsend, J., Kang, N. & Barber, D. Parallel neural local lossless compression. ar**v preprint http://arxiv.org/abs/2201.05213ar**v:2201.05213 (2022)
Zhou M, Gao W, Jiang M, Yu H (2012) Hevc lossless coding and improvements. IEEE Transactions on Circuits and Systems for Video Technology 22(12):1839–1843
Funding
No funding was received for conducting this study.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gümüş, S., Kamisli, F. A learned pixel-by-pixel lossless image compression method with 59K parameters and parallel decoding. Multimed Tools Appl 83, 22975–22993 (2024). https://doi.org/10.1007/s11042-023-16270-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16270-4