Adaptive multi-modal fusion of spatially variant kernel refinement with diffusion model for blind image super-resolution

J Lin, Y Wang, Z Tao, B Wang, Q Zhao, H Wang… - … on Computer Vision, 2025 - Springer
Pre-trained diffusion models utilized for image generation encapsulate a substantial
reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of …

Suppressing uncertainties in degradation estimation for blind super-resolution

J Lin, Z Tao, X Tong, X Mai, H Wang, B Wang… - Proceedings of the …, 2024 - dl.acm.org
The problem of blind image super-resolution aims to recover high-resolution (HR) images
from low-resolution (LR) images with unknown degradation modes. Most existing methods …