Variable Rate Image Compression Method with Dead-Zone Quantizer

Jing Zhou, Akira Nakagawa, Keizo Kato, Sihan Wen, Kimihiko Kazui, Zhiming Tan

CVPRW 2020 pp. 624-628

doi:10.1109/CVPRW50498.2020.00089 /cvprw/2020/zhou2020cvprw-variable/

Abstract

Deep learning based image compression methods have achieved superior performance compared with transform based conventional codec. With end-to-end Rate-Distortion Optimization (RDO) in the codec, compression model is optimized with Lagrange multiplier λ. For conventional codec, signal is decorrelated with orthonormal transformation, and uniform quantizer is introduced. We propose a variable rate image compression method with dead-zone quantizer. Firstly, the autoencoder network is trained with RaDOGAGA [6] framework, which can make the latents isometric to the metric space, such as SSIM and MSE. Then the conventional dead-zone quantization method with arbitrary step size is used in the common trained network to provide the flexible rate control. With dead-zone quantizer, the experimental results show that our method performs comparably with independently optimized models within a wide range of bitrate.

PDF CVPRW Semantic Scholar

Cite

Text

Zhou et al. "Variable Rate Image Compression Method with Dead-Zone Quantizer." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00089

Markdown

[Zhou et al. "Variable Rate Image Compression Method with Dead-Zone Quantizer." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/zhou2020cvprw-variable/) doi:10.1109/CVPRW50498.2020.00089

BibTeX

@inproceedings{zhou2020cvprw-variable,
  title     = {{Variable Rate Image Compression Method with Dead-Zone Quantizer}},
  author    = {Zhou, Jing and Nakagawa, Akira and Kato, Keizo and Wen, Sihan and Kazui, Kimihiko and Tan, Zhiming},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {624-628},
  doi       = {10.1109/CVPRW50498.2020.00089},
  url       = {https://mlanthology.org/cvprw/2020/zhou2020cvprw-variable/}
}