Image De-Quantization Using Generative Models as Priors
This work addresses the problem of reversing image quantization for applications like compression and restoration, offering a novel approach with practical robustness.
The paper tackles the ill-posed problem of image de-quantization by developing a method based on statistical estimation theory and generative models as priors, which successfully recovers images from severe quantization effects and can handle unknown parameters in the quantization process.
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.