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.

我们提出了第一个实用的学习无损图像压缩系统 L3C，它在压缩方面优于流行的人工编码器 PNG、WebP 和 JPEG 2000。L3C 的核心是一种可完全并行化的分层自适应熵编码概率模型，该模型针对压缩任务进行了端到端的优化。与最近的自回归离散概率模型（如 PixelCNN）相比，我们的方法将图像分布与学习的辅助表示一起建模，而不是仅在 RGB 空间中建模图像分布，并且只需要三个前向传递来预测所有像素的概率，而不是为每个像素分别预测一个。此外，我们发现学习辅助表示至关重要，而且显著优于预定义的辅助表示，如 RGB 金字塔。