1 code implementation • CVPR 2023 • Ji Li, Weixi Wang, Yuesong Nan, Hui Ji
In contrast, this paper presents a dataset-free deep learning method for removing uniform and non-uniform blur effects from images of static scenes.
no code implementations • CVPR 2020 • Yuesong Nan, Hui Ji
It is known that non-blind deconvolution is susceptible to such a kernel/model error.
no code implementations • CVPR 2020 • Yuesong Nan, Yuhui Quan, Hui Ji
Based on the framework of variational expectation maximization (EM), an iterative noise-blind deblurring scheme is proposed which integrates the estimation of noise level and the quantification of image prior uncertainty.