Abstract | ||
---|---|---|
In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimization and performance-improving normalization layers in the auto-encoder. We evaluate and show the incremental performance increase of each of our contributions. |
Year | Venue | DocType |
---|---|---|
2018 | CVPR Workshops | Conference |
Volume | Citations | PageRank |
abs/1805.10887 | 0 | 0.34 |
References | Authors | |
7 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Çaglar Aytekin | 1 | 6 | 1.57 |
Xingyang Ni | 2 | 5 | 1.21 |
Francesco Cricri | 3 | 64 | 11.77 |
Jani Lainema | 4 | 415 | 39.62 |
Emre Aksu | 5 | 7 | 7.00 |
M. M. Hannuksela | 6 | 376 | 80.61 |