Generative Compression

  title={Generative Compression},
  author={Shibani Santurkar and David Budden and Nir Shavit},
  journal={2018 Picture Coding Symposium (PCS)},
Traditional image and video compression algorithms rely on hand-crafted encoder/decoder pairs (codecs) that lack adaptability and are agnostic to the data being compressed. We describe the concept of generative compression, the compression of data using generative models, and suggest that it is a direction worth pursuing to produce more accurate and visually pleasing reconstructions at deeper compression levels for both image and video data. We also show that generative compression is orders… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 247 times over the past 90 days. VIEW TWEETS
9 Citations
46 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 46 references

Similar Papers

Loading similar papers…