Spatially adaptive image compression using a tiled deep network

Troy T. Chinen
Troy T. Chinen
Joel Shor
Joel Shor
Damien Vincent
Damien Vincent

international conference on image processing, 2017.

Cited by: 28|Bibtex|Views137|
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant spatial bit rate across each image. While entropy coding introduces some spatial variation, traditional ...More

Code:

Data:

Your rating :
0

 

Tags
Comments