Can I read COIN: COmpression with Implicit Neural representations on EtoBox?

COIN: COmpression with Implicit Neural representations by Dupont, Emilien; Goliński, Adam; Alizadeh, Milad; Teh, Yee Whye; Doucet, Arnaud is a scholarly article available to read on EtoBox.

What is COIN: COmpression with Implicit Neural representations about?

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.

Author

Dupont, Emilien; Goliński, Adam; Alizadeh, Milad; Teh, Yee Whye; Doucet, Arnaud

Published

2021

Language

EN