Accelerated Deep Lossless Image Coding with Unified Paralleleized GPU Coding Architecture
Benjamin Lukas Cajus Barzen, Fedor Glazov, Jonas Geistert, Thomas Sikora
We propose Deep Lossless Image Coding (DLIC), a full resolution learned
lossless image compression algorithm. Our algorithm is based on a neural
network combined with an entropy encoder. The neural network performs a density
estimation on each pixel of the source image. The density estimation is then
used to code the target pixel, beating FLIF in terms of compression rate.
Similar approaches have been attempted. However, long run times make them
unfeasible for real world applications. We introduce a parallelized GPU based
implementation, allowing for encoding and decoding of grayscale, 8-bit images
in less than one second. Because DLIC uses a neural network to estimate the
probabilities used for the entropy coder, DLIC can be trained on domain
specific image data. We demonstrate this capability by adapting and training
DLIC with Magnet Resonance Imaging (MRI) images.