Deep Model-Based Super-Resolution with Non-uniform Blur - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Deep Model-Based Super-Resolution with Non-uniform Blur

Résumé

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.

Dates et versions

hal-03787320 , version 1 (24-09-2022)

Identifiants

Citer

Charles Laroche, Andrés Almansa, Matias Tassano. Deep Model-Based Super-Resolution with Non-uniform Blur. Winter Conference on Applications of Computer Vision (WACV 2023), IEEE/CVF, Jan 2023, Waikoloa, Hawaii, U.S. Outlying Islands. pp.1797-1808, ⟨10.1109/WACV56688.2023.00184⟩. ⟨hal-03787320⟩
84 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More