TY - GEN
T1 - Learned Lossless Image Compression with A Hyperprior and Discretized Gaussian Mixture Likelihoods
AU - Cheng, Zhengxue
AU - Sun, Heming
AU - Takeuchi, Masaru
AU - Katto, Jiro
N1 - Funding Information:
The authors would like to thank Fabian Mentzer (the first author of L3C) for fruitful discussion and insightful feedback on the evaluation methods and datasets. This work was supported in part by the Japan Society for the Promotion of Science (JSPS) Research Fellowship DC2 Grant Number 201914620, in part by JST, PRESTO Grant Number JPMJPR19M5, Japan.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - 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.
AB - 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.
KW - Deep Learning
KW - Gaussian Mixture Model
KW - HyperPrior
KW - Lossless Image Compression
UR - http://www.scopus.com/inward/record.url?scp=85089245756&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089245756&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053413
DO - 10.1109/ICASSP40776.2020.9053413
M3 - Conference contribution
AN - SCOPUS:85089245756
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2158
EP - 2162
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -