ML Anthology

Rate-Distortion Optimized Learning-Based Image Compression Using an Adaptive Hierachical Autoencoder with Conditional Hyperprior

Fabian Brand, Kristian Fischer, André Kaup
CVPRW 2021 pp. 1885-1889
doi:10.1109/CVPRW53098.2021.00211 /cvprw/2021/brand2021cvprw-ratedistortion/

Abstract

Deep-learning-based compressive autoencoders consist of a single non-linear function mapping the image to a latent space which is quantized and transmitted. Afterwards, a second non-linear function transforms the received latent space back to a reconstructed image. This method achieves superior quality than many traditional image coders, which is due to a non-linear generalization of linear transforms used in traditional coders. However, modern image and video coder achieve large coding gains by applying rate-distortion optimization on dynamic block-partitioning. In this paper, we present RDONet, a novel approach to achieve similar effects in compression with full image autoencoders by using different hierarchical levels, which are transmitted adaptively after performing an external rate-distortion optimization. Using our model, we are able to save up to 20% rate over comparable non-hierarchical models while maintaining the same quality.

PDF CVPRW Semantic Scholar

Cite

Text

Brand et al. "Rate-Distortion Optimized Learning-Based Image Compression Using an Adaptive Hierachical Autoencoder with Conditional Hyperprior." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00211

Markdown

[Brand et al. "Rate-Distortion Optimized Learning-Based Image Compression Using an Adaptive Hierachical Autoencoder with Conditional Hyperprior." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/brand2021cvprw-ratedistortion/) doi:10.1109/CVPRW53098.2021.00211

BibTeX

@inproceedings{brand2021cvprw-ratedistortion,
  title     = {{Rate-Distortion Optimized Learning-Based Image Compression Using an Adaptive Hierachical Autoencoder with Conditional Hyperprior}},
  author    = {Brand, Fabian and Fischer, Kristian and Kaup, André},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {1885-1889},
  doi       = {10.1109/CVPRW53098.2021.00211},
  url       = {https://mlanthology.org/cvprw/2021/brand2021cvprw-ratedistortion/}
}