Lossy Image Compression with Compressive Autoencoders [article]

Lucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Huszár
2017 arXiv   pre-print
We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are
more » ... nt to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs. Our network is furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images. This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower architectures, computationally expensive methods, or focusing on small images.
arXiv:1703.00395v1 fatcat:ftno22l3tvbhthllmgomabdxtq