no code implementations • 15 Mar 2024 • Xijun Wang, Santiago López-Tapia, Alice Lucas, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos
To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process.
no code implementations • 12 Feb 2024 • Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos
Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth's surface.
no code implementations • 8 May 2023 • Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos
We use the learned information to further condition the diffusion model.
1 code implementation • 16 Nov 2020 • Santiago López-Tapia, Nicolás Pérez de la Blanca
Our approach leverages the degradation model and proposes a new formulation of the Convolutional Neural Network (CNN) cascade model, where each network sub-module is constrained to solve a specific degradation: deblurring or upsampling.
no code implementations • 2 Jul 2019 • Santiago López-Tapia, Alice Lucas, Rafael Molina, Aggelos K. Katsaggelos
The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions.