Hypernetwork-Based Adaptive Image Restoration
This addresses the problem of efficient and versatile image restoration for computer vision applications, offering a practical solution with reduced parameters.
The paper tackles adaptive image restoration for multiple degradation levels with a single fixed-size model, achieving state-of-the-art results in size and accuracy across tasks like denoising, deJPEG, and super-resolution on popular datasets.
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.