Practical Full Resolution Learned Lossless Image Compression
This work addresses the need for efficient lossless image compression for applications requiring high-quality storage or transmission, representing a novel method rather than an incremental improvement.
The authors tackled the problem of learned lossless image compression by introducing L3C, a practical system that outperforms PNG, WebP, and JPEG 2000, achieving over two orders of magnitude speedup compared to PixelCNN variants.
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical probabilistic model for adaptive entropy coding which is optimized end-to-end for the compression task. In contrast to recent autoregressive discrete probabilistic models such as PixelCNN, our method i) models the image distribution jointly with learned auxiliary representations instead of exclusively modeling the image distribution in RGB space, and ii) only requires three forward-passes to predict all pixel probabilities instead of one for each pixel. As a result, L3C obtains over two orders of magnitude speedups when sampling compared to the fastest PixelCNN variant (Multiscale-PixelCNN). Furthermore, we find that learning the auxiliary representation is crucial and outperforms predefined auxiliary representations such as an RGB pyramid significantly.