COIN: COmpression with Implicit Neural representations

03/03/2021
by   Emilien Dupont, et al.
0

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.

READ FULL TEXT
research
01/30/2022

COIN++: Data Agnostic Neural Compression

Neural compression algorithms are typically based on autoencoders that r...
research
07/08/2022

L_0onie: Compressing COINs with L_0-constraints

Advances in Implicit Neural Representations (INR) have motivated researc...
research
11/30/2018

Practical Full Resolution Learned Lossless Image Compression

We propose the first practical learned lossless image compression system...
research
05/30/2023

Compression with Bayesian Implicit Neural Representations

Many common types of data can be represented as functions that map coord...
research
11/19/2012

Five Modulus Method For Image Compression

Data is compressed by reducing its redundancy, but this also makes the d...
research
05/29/2018

CocoNet: A deep neural network for mapping pixel coordinates to color values

In this paper, we propose a deep neural network approach for mapping the...
research
02/08/2023

Hyperspectral Image Compression Using Implicit Neural Representation

Hyperspectral images, which record the electromagnetic spectrum for a pi...

Please sign up or login with your details

Forgot password? Click here to reset