Target-Quality Image Compression with Recurrent, Convolutional Neural Networks

Sung Jin Hwang
Sung Jin Hwang
Joel Shor
Joel Shor
Damien Vincent
Damien Vincent

arXiv: Computer Vision and Pattern Recognition, Volume abs/1705.06687, 2017.

Cited by: 15|Bibtex|Views103
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lowe...More

Code:

Data:

Your rating :
0

 

Tags
Comments