Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning - Intelligent Systems. According to news reporting originating in Chengdu, People's Republic of China, by NewsRx journalists, research stated, "B lind face deblurring aims to recover a sharper face from its unknown degraded ve rsion (i.e., different motion blur, noise). However, most previous works typical ly rely on degradation facial priors extracted from low-quality inputs, which ge nerally leads to unlifelike deblurring results." Funders for this research include National Natural Science Foundation of China ( NSFC), Sichuan Science and Technology program. The news reporters obtained a quote from the research from the Chengdu Universit y of Information and Technology, "In this paper, we propose a multi-scale progre ssive face-deblurring generative adversarial network (MPFD-GAN) that requires no facial priors to generate more realistic multi-scale deblurring results by one feed-forward process. Specifically, MPFD-GAN mainly includes two core modules: t he feature retention module and the texture reconstruction module (TRM). The for mer can capture non-local similar features by full advantage of the different re ceptive fields, which facilitates the network to recover the complete structure. The latter adopts a supervisory attention mechanism that fully utilizes the rec overed low-scale face to refine incoming features at every scale before propagat ing them further. Moreover, TRM extracts the high-frequency texture information from the recovered low-scale face by the Laplace operator, which guides subseque nt steps to progressively recover faithful face texture details."
NETL
NSTL