Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

COIN: COmpression with Implicit Neural representations

  • Emilien DupontUniversity of Oxford
  • Adam GolińskiUniversity of Oxford
  • Milad AlizadehUniversity of Oxford
  • Yee Whye TehUniversity of Oxford
  • Arnaud DoucetUniversity of Oxford

Neural Compression Workshop at ICLR, 2021

Abstract

We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image. Specifically, to encode an image, we fit it with an MLP which maps pixel locations to RGB values. We then quantize and store the weights of this MLP as a code for the image. To decode the image, we simply evaluate the MLP at every pixel location. We found that this simple approach outperforms JPEG at low bit-rates, even without entropy coding or learning a distribution over weights. While our framework is not yet competitive with state of the art compression methods, we show that it has various attractive properties which could make it a viable alternative to other neural data compression approaches.

Materials

  • PDF
  • Code
BibTeX
@misc{dupont2021coin,
  title = {{COIN: COmpression with Implicit Neural representations}},
  author = {Dupont, Emilien and Goliński, Adam and Alizadeh, Milad and Teh, Yee Whye and Doucet, Arnaud},
  year = {2021},
  booktitle = {Neural Compression Workshop at ICLR}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub