Efficient Context-Aware Lossy Image Compression

Jan Xu, Alex Lytchier, Ciro Cursio, Dimitrios Kollias, Chri Besenbruch, Arsalan Zafar

CVPRW 2020 pp. 552-554

doi:10.1109/CVPRW50498.2020.00073 /cvprw/2020/xu2020cvprw-efficient/

Abstract

We present an efficient context-aware lossy image compression system to participate in the Low Rate track of the CLIC 2020 Image Compression challenge. Our method is based on an autoencoder pipeline augmented with a nested hyperprior model, a PixelCNN-based context model and an adversarial loss to remove artefacts.

CVPRW Semantic Scholar

Cite

Text

Xu et al. "Efficient Context-Aware Lossy Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00073

Markdown

[Xu et al. "Efficient Context-Aware Lossy Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/xu2020cvprw-efficient/) doi:10.1109/CVPRW50498.2020.00073

BibTeX

@inproceedings{xu2020cvprw-efficient,
  title     = {{Efficient Context-Aware Lossy Image Compression}},
  author    = {Xu, Jan and Lytchier, Alex and Cursio, Ciro and Kollias, Dimitrios and Besenbruch, Chri and Zafar, Arsalan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {552-554},
  doi       = {10.1109/CVPRW50498.2020.00073},
  url       = {https://mlanthology.org/cvprw/2020/xu2020cvprw-efficient/}
}