On learning optimized reaction diffusion processes for effective image restoration

TL;DR

This paper introduces a trainable reaction diffusion model for image restoration that achieves high performance with low computational cost, suitable for GPU acceleration.

Contribution

It extends traditional reaction diffusion models with parametrized filters and influence functions, trained via a loss-based approach for improved image restoration.

Findings

Achieves state-of-the-art performance on standard datasets.

Highly efficient and suitable for parallel GPU implementation.

Training the parameters significantly improves restoration quality.

Abstract

For several decades, image restoration remains an active research topic in low-level computer vision and hence new approaches are constantly emerging. However, many recently proposed algorithms achieve state-of-the-art performance only at the expense of very high computation time, which clearly limits their practical relevance. In this work, we propose a simple but effective approach with both high computational efficiency and high restoration quality. We extend conventional nonlinear reaction diffusion models by several parametrized linear filters as well as several parametrized influence functions. We propose to train the parameters of the filters and the influence functions through a loss based approach. Experiments show that our trained nonlinear reaction diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for image restoration. Due to their structural simplicity, our trained models are highly efficient and are also well-suited for parallel computation on GPUs.