Learning Better Lossless Compression Using Lossy Compression - Crossminds
CrossMind.ai logo
Authors: Fabian Mentzer, Luc Van Gool, Michael Tschannen Description: We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual. We then model the distribution of the residual with a convolutional neural network-based probabilistic model that is conditioned on the BPG reconstruction, and combine it with entropy coding to losslessly encode the residual. Finally, the image is stored using the concatenation of the bitstreams produced by BPG and the learned residual coder. The resulting compression system achieves state-of-the-art performance in learned lossless full-resolution image compression, outperforming previous learned approaches as well as PNG, WebP, and JPEG2000.
Reactions (0) | Note
    📝 No reactions yet
    Be the first one to share your thoughts!