Deep Image Compression with Latent Optimization and Piece-Wise Quantization Approximation

Abstract

Benefit from its capability of learning high-dimensional compact representation from raw data, the auto-encoders are widely used in various tasks of data compression. In particular, for deep image compression, auto-encoders generally take the responsibility of mapping original images to the latent representation to be coded. In this paper, we propose a new framework for deep image compression by devising a loss function for latent optimization, and adopting the differentiable approximation of quantization. In our experiments, both subjective and objective results can confirm the effectiveness of our contributions.

Cite

Text

Wu et al. "Deep Image Compression with Latent Optimization and Piece-Wise Quantization Approximation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00219

Markdown

[Wu et al. "Deep Image Compression with Latent Optimization and Piece-Wise Quantization Approximation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/wu2021cvprw-deep/) doi:10.1109/CVPRW53098.2021.00219

BibTeX

@inproceedings{wu2021cvprw-deep,
  title     = {{Deep Image Compression with Latent Optimization and Piece-Wise Quantization Approximation}},
  author    = {Wu, Yuyang and Qi, Zhiyang and Zheng, Huiming and Tao, Lvfang and Gao, Wei},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {1926-1930},
  doi       = {10.1109/CVPRW53098.2021.00219},
  url       = {https://mlanthology.org/cvprw/2021/wu2021cvprw-deep/}
}