Noise generation for compression algorithms

TL;DR

This paper introduces a biologically inspired noise generation technique for lossy compression that enhances the realism of decompressed images by adding learned noise during decoding, with minimal additional memory.

Contribution

It proposes a novel noise modeling approach integrated into compression algorithms, improving image realism without significant overhead.

Findings

Significantly increases decompressed image realism

Adds minimal memory overhead

Applicable across various image sizes

Abstract

In various Computer Vision and Signal Processing applications, noise is typically perceived as a drawback of the image capturing system that ought to be removed. We, on the other hand, claim that image noise, just as texture, is important for visual perception and, therefore, critical for lossy compression algorithms that tend to make decompressed images look less realistic by removing small image details. In this paper we propose a physically and biologically inspired technique that learns a noise model at the encoding step of the compression algorithm and then generates the appropriate amount of additive noise at the decoding step. Our method can significantly increase the realism of the decompressed image at the cost of few bytes of additional memory space regardless of the original image size. The implementation of our method is open-sourced and available at https://github.com/google/pik.