On learning optimized reaction diffusion processes for effective image restoration
This work addresses the trade-off between performance and computational efficiency in image restoration, which is crucial for practical applications in low-level computer vision, though it is incremental as it builds on existing reaction diffusion models.
The authors tackled the problem of high computational cost in state-of-the-art image restoration methods by proposing a trained nonlinear reaction diffusion model with parametrized filters and influence functions, achieving the best reported performance on common test datasets while maintaining high efficiency and suitability for GPU parallel computation.
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.