Extreme Image Compression via Multiscale Autoencoders With Generative Adversarial Optimization

@article{Huang2019ExtremeIC,
  title={Extreme Image Compression via Multiscale Autoencoders With Generative Adversarial Optimization},
  author={Chao Huang and Haojie Liu and Tong Chen and Shiliang Pu and Qiu Shen and Zhan Ma},
  journal={CoRR},
  year={2019},
  volume={abs/1904.03851}
}
We propose a MultiScale AutoEncoder (MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the “priors” at different resolution scale to improve the compression efficiency, and also employs the generative adversarial network (GAN) with multiscale discriminators to perform the end-to-end trainable rate-distortion optimization. We compare the perceptual quality of our reconstructions with traditional compression… CONTINUE READING
4
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 23 REFERENCES

Efficient Nonlinear Transforms for Lossy Image Compression

  • 2018 Picture Coding Symposium (PCS)
  • 2018
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Least Squares Generative Adversarial Networks

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Scene Parsing through ADE20K Dataset

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

The Cityscapes Dataset for Semantic Urban Scene Understanding

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Conditional Generative Adversarial Nets

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Nets

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Bpg image format

Bellard
  • https://bellard.org/bpg/.
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…