Lossless image compression is an important task in the field of multimedia communication. Traditional image codecs typically support lossless mode, such as WebP, JPEG2000, FLIF. Recently, deep learning based approaches have started to show the potential at this point. HyperPrior is an effective technique proposed for lossy image compression. This paper generalizes the hyperprior from lossy model to lossless compression, and proposes a L2-norm term into the loss function to speed up training procedure. Besides, this paper also investigated different parameterized models for latent codes, and propose to use Gaussian mixture likelihoods to achieve adaptive and flexible context models. Experimental results validate our method can outperform existing deep learning based lossless compression, and outperform the JPEG2000 and WebP for JPG images.
@article{arxiv.2002.01657,
title = {Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods},
author = {Zhengxue Cheng and Heming Sun and Masaru Takeuchi and Jiro Katto},
journal= {arXiv preprint arXiv:2002.01657},
year = {2020}
}