Image De-Quantization Using Generative Models as Priors

TL;DR

This paper introduces a mathematically grounded de-quantization method that leverages generative models as priors to recover images affected by severe quantization, even with unknown quantization parameters.

Contribution

It develops a novel de-quantization approach based on statistical estimation theory and generative priors, capable of handling unknown quantization parameters.

Findings

Successfully de-quantizes severely quantized images

Recovers images with unknown quantization parameters

Simple and effective method based on rigorous analysis

Abstract

Image quantization is used in several applications aiming in reducing the number of available colors in an image and therefore its size. De-quantization is the task of reversing the quantization effect and recovering the original multi-chromatic level image. Existing techniques achieve de-quantization by imposing suitable constraints on the ideal image in order to make the recovery problem feasible since it is otherwise ill-posed. Our goal in this work is to develop a de-quantization mechanism through a rigorous mathematical analysis which is based on the classical statistical estimation theory. In this effort we incorporate generative modeling of the ideal image as a suitable prior information. The resulting technique is simple and capable of de-quantizing successfully images that have experienced severe quantization effects. Interestingly, our method can recover images even if the quantization process is not exactly known and contains unknown parameters.