ML Anthology

Block-Optimized Variable Bit Rate Neural Image Compression

Çaglar Aytekin, Xingyang Ni, Francesco Cricri, Jani Lainema, Emre Aksu, Miska M. Hannuksela
CVPRW 2018 pp. 2551-2554
/cvprw/2018/aytekin2018cvprw-blockoptimized/

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, entropyfriendly 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.

PDF CVPRW Semantic Scholar

Cite

Text

Aytekin et al. "Block-Optimized Variable Bit Rate Neural Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.

Markdown

[Aytekin et al. "Block-Optimized Variable Bit Rate Neural Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/aytekin2018cvprw-blockoptimized/)

BibTeX

@inproceedings{aytekin2018cvprw-blockoptimized,
  title     = {{Block-Optimized Variable Bit Rate Neural Image Compression}},
  author    = {Aytekin, Çaglar and Ni, Xingyang and Cricri, Francesco and Lainema, Jani and Aksu, Emre and Hannuksela, Miska M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {2551-2554},
  url       = {https://mlanthology.org/cvprw/2018/aytekin2018cvprw-blockoptimized/}
}