Hypernetwork-Based Adaptive Image Restoration

TL;DR

This paper introduces a hypernetwork-based adaptive image restoration method that achieves state-of-the-art accuracy across various tasks with fewer parameters and a single fixed-size model, adaptable to different degradation levels at inference.

Contribution

The proposed approach is the first to use a hypernetwork to enable a single fixed-size model for multiple degradation levels, reducing parameters while maintaining high accuracy.

Findings

State-of-the-art results on popular datasets

Significant reduction in model size

Versatile across denoising, deJPEG, and super-resolution

Abstract

Adaptive image restoration models can restore images with different degradation levels at inference time without the need to retrain the model. We present an approach that is highly accurate and allows a significant reduction in the number of parameters. In contrast to existing methods, our approach can restore images using a single fixed-size model, regardless of the number of degradation levels. On popular datasets, our approach yields state-of-the-art results in terms of size and accuracy for a variety of image restoration tasks, including denoising, deJPEG, and super-resolution.