Real-Time Adaptive Image Compression

Oren Rippel, Lubomir Bourdev
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:2922-2930, 2017.

Abstract

We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces file sizes 3 times smaller than JPEG, 2.5 times smaller than JPEG 2000, and 2.3 times smaller than WebP on datasets of generic images across a spectrum of quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in less than 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-rippel17a, title = {Real-Time Adaptive Image Compression}, author = {Oren Rippel and Lubomir Bourdev}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {2922--2930}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/rippel17a/rippel17a.pdf}, url = {https://proceedings.mlr.press/v70/rippel17a.html}, abstract = {We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces file sizes 3 times smaller than JPEG, 2.5 times smaller than JPEG 2000, and 2.3 times smaller than WebP on datasets of generic images across a spectrum of quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in less than 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates.} }
Endnote
%0 Conference Paper %T Real-Time Adaptive Image Compression %A Oren Rippel %A Lubomir Bourdev %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-rippel17a %I PMLR %P 2922--2930 %U https://proceedings.mlr.press/v70/rippel17a.html %V 70 %X We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces file sizes 3 times smaller than JPEG, 2.5 times smaller than JPEG 2000, and 2.3 times smaller than WebP on datasets of generic images across a spectrum of quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in less than 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates.
APA
Rippel, O. & Bourdev, L.. (2017). Real-Time Adaptive Image Compression. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:2922-2930 Available from https://proceedings.mlr.press/v70/rippel17a.html.

Related Material