Block based learned image compression
Pages 26495 - 26509
Abstract
Efficient image compression is very important for storage, retrieval, processing and transmission of image contents. The objective is to find a striking balance between compression ratio and the distortion in image. Recently, there has been a rise in interest on lossy neural network based compression algorithms. Specifically, autoencoder based compression schemes have shown great potential in learned image compression domain. This paper proposes a new algorithm for learned image compression using block based Generative Adversarial Networks. The adversarial network was trained on the blocks derived from a large image data-set. The compressed images were compared against standard compression schemes such as JPEG, PNG to show the comparative strength of block based learned compression algorithms. It has been found that performance of algorithm drops significantly at low bits per pixel. So, the paper compares the algorithm performance at various bpp values.
References
[1]
AlirezaMakhzani BF (2017) PixelGANautoencoders. In: Proceedings of 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach
[2]
Atienza R (2017) GAN by example using Keras on tensorflow backend. Available at: https://towardsdatascience.com/gan-by-example-using-keras-ontensorflow-backend-1a6d515a60d0, Accessed Mar 2023
[3]
Cheng Z, Sun H, Takeuchi M, Katto J (2020) Learned image compression with discretized gaussian mixture likelihoods and attention modules. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Jun 14-19, 2020, Online, pp 7939–7948
[4]
Chollet F (2016) Building autoencoders in Keras. The Keras Blogs. Available at: https://blog.keras.io/building-autoencoders-in-keras.html, Accessed Mar 2023
[5]
Constine J (2012) TechCrunch. Available at: https://techcrunch.com/2012/08/22/howbig-is-facebooks-data-2-5-billion-pieces-of-content-and-500-terabytesingested-every-day. Accessed Jan 2019
[6]
Dhawan S (2011) A review of image compression and comparison of its algorithms. Int J Electron Commun Technol 2(1):22–26
[7]
DL4J. GAN: A beginner’s guide to generative adversarial networks (2017) Available at: https://mgubaidullin.github.io/deeplearning4j-docs/generative-adversarial-network.html. Accessed Mar 2023
[8]
EirikurAgustsson FM, Tschannen M (2019) Generative adversarial networks for extreme learned image compression. In: Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), Seoul
[9]
Galteri L (2017) Deep generative adversarial compression artifact removal. In: Proceedings of International Conference on Computer Vision, Venice
[10]
Goodfellow I (2016) Generative adversarial networks. NIPS Tutorial 2016. Available at: https://arxiv.org/pdf/1701.00160
[11]
Goodfellow ACI, Bengio Y (2016) “Deep learning”. MIT Press. http://www.deeplearningbook.org
[12]
Guido RC (2018) A tutorial review on entropy-based handcrafted feature extraction for information fusion. Inf Fusion 41:161–175
[13]
Hui J (2018) GAN — ways to improve GAN performance. Towards Data Science. https://towardsdatascience.com/gan-ways-to-improve-gan-performance-acf37f9f59b. Accessed Mar 2023
[14]
Turner V, Gantz JF, Reinsel D, Minton S (2014) The digital universe of opportunities: Rich data and the increasing value of the internet of things. IDC Analyze the Future 16:13–19
[15]
Khalil MI (2010) Image compression using new entropy coder. Int J Comput Theory Eng 2(3):39–41
[16]
Khedr WM (2016) Image compression using DCT upon various quantization. Int J Comput Appl 137(1):11–13
[17]
Ledig C (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu
[18]
Liu Z, Liu T, Wen W, Jiang L, Xu J, Wang Y, Quan G (2018) “DeepN-JPEG: A deep neural network favorable jpeg-based image compression framework”. In proceedings of 55th Annual Design Automation Conference, San Francisco California
[19]
Liu MY, Huang X, Yu J, Wang TC, and Mallya A Generative adversarial networks for image and video synthesis: Algorithms and applications Proc IEEE 2021 109 5 839-862
[20]
Makhzani A (2016) Adversarial autoencoders. In: Proceedings of International Conference on Learning Representations, San Juan
[21]
Minnen D, Ballé J, Toderici GD (2018) Joint autoregressive and hierarchical priors for learned image compression. In: Proceedings of Neural Information Processing Systems, Montreal
[22]
Qureshi M, Rai A, Islam N, and Sheikh G A four-pronged low cost and optimized traffic routing solution Int J Interact Mob Technol 2020 4 10 46-60
[23]
Santurkar S, Budden D, Shavit N (2018) Generative compression. In: 2018 Picture Coding Symposium (PCS). IEEE, pp 258–262
[24]
Saxena D, Cao J (2021) Generative adversarial networks (GANs) challenges, solutions, and future directions. ACM Comput Surv (CSUR) 54(3):1–42
[25]
Statista (2017) The statistics portal. https://www.statista.com/topics/2019/youtube. Accessed Mar 2023
[26]
Workshop and challenge on learned image compression (2018) IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City
[27]
Wu L, Huang K, Shen H (2020) A GAN-based tunable image compression system. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 2334–2342
Recommendations
Learning-driven lossy image compression: A comprehensive survey
AbstractIn the field of image processing and computer vision (CV), machine learning (ML) architectures are widely used. Image compression problems can be solved using convolutional neural networks (CNNs). As a result of bandwidth and memory constraints, ...
Highlights- Discussion about the background of image compression.
- Classification of image compression frameworks into subgroups based on architectures.
- Insight about open research problems and future research directions in learning-driven ...
WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model
Computer Vision – ECCV 2024AbstractRecently learned image compression (LIC) has achieved great progress and even outperformed the traditional approach using DCT or discrete wavelet transform (DWT). However, LIC mainly reduces spatial redundancy in the autoencoder networks and ...
Sub-block interchange for lossless image compression
Lempel-Ziv-Welch (LZW) technique for text compression has been successfully modified to lossless image compression such as GIF. A new class of text compression, namely, Burrows and Wheeler (1994) transformation (BWT) has been developed which gives ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023. 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.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 07 March 2023
Accepted: 22 February 2023
Revision received: 23 September 2022
Received: 28 February 2022
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in