Deep Model-Based Super-Resolution with Non-uniform Blur
This addresses the problem of image restoration for applications like photography or medical imaging where blur varies spatially, representing an incremental improvement over existing uniform blur methods.
The paper tackles super-resolution with non-uniform blur, a more realistic but computationally challenging case compared to uniform blur assumptions, by proposing a deep plug-and-play algorithm and unfolding it into an end-to-end trainable network, achieving remarkable performance and generalization across various blur kernels, noise levels, and scale factors.
We propose a state-of-the-art method for super-resolution with non-uniform blur. Single-image super-resolution methods seek to restore a high-resolution image from blurred, subsampled, and noisy measurements. Despite their impressive performance, existing techniques usually assume a uniform blur kernel. Hence, these techniques do not generalize well to the more general case of non-uniform blur. Instead, in this paper, we address the more realistic and computationally challenging case of spatially-varying blur. To this end, we first propose a fast deep plug-and-play algorithm, based on linearized ADMM splitting techniques, which can solve the super-resolution problem with spatially-varying blur. Second, we unfold our iterative algorithm into a single network and train it end-to-end. In this way, we overcome the intricacy of manually tuning the parameters involved in the optimization scheme. Our algorithm presents remarkable performance and generalizes well after a single training to a large family of spatially-varying blur kernels, noise levels and scale factors.