We proposed an end-to-end framework to handle general motion blurs with a unified deep neural network, and optimize the shutter’s encoding pattern together with the deblurring processing to achieve high-quality sharp images.
Under low-light environment, handheld photography suffers from severe camera shake under long exposure settings. Sophisticated noise and saturation regions are two dominating challenges in practical low-light deblurring. In this work, we propose a novel non-blind deblurring method dubbed image and feature space Wiener deconvolution network (INFWIDE) to tackle these problems systematically.
In this paper, we propose to build a dual-sensor camera to additionally collect the photons in NIR wavelength, and make use of the correlation between RGB and near-infrared (NIR) spectrum to perform high-quality reconstruction from noisy dark video pairs.