Adaptive Aggregation Network for Face Hallucination

Jin, Guo; Han, Zhen; Liu, Han; Wang, Zhongyuan; Hu, Ruimin

doi:10.1007/978-3-030-00767-6_18

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local Methods: Although global methods can capture global information, they ignore the differences among different facial regions, thereby to difficulty of learning and a decrease in the performance of the model. To settle this problem, adaptive aggregation network (AAN) [51], a method to deal with noise face super-resolution, is proposed, including two generator branches and an aggregation branch. To deal with each case on its merits, the aggregation branch is designed to generate a mask M with input LR, and then M and 1 − M are used as the mask to be applied on the output of two generator branches respectively.…”

Section: General Face Super-resolution Methodsmentioning

confidence: 99%

Deep Learning-based Face Super-Resolution: A Survey

Jiang¹,

Wang²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Face super-resolution, also known as face hallucination, which is aimed at enhancing the resolution of low-resolution (LR) one or a sequence of face images to generate the corresponding high-resolution (HR) face images, is a domain-specific image super-resolution problem. Recently, face super-resolution has received considerable attention, and witnessed dazzling advances with deep learning techniques. To date, few summaries of the studies on the deep learning-based face super-resolution are available. In this survey, we present a comprehensive review of deep learning techniques in face super-resolution in a systematic manner. First, we summarize the problem formulation of face super-resolution. Second, we compare the differences between generic image super-resolution and face super-resolution. Third, datasets and performance metrics commonly used in facial hallucination are presented. Fourth, we roughly categorize existing methods according to the utilization of face-specific information. In

show abstract

Section: General Face Super-resolution Methodsmentioning

confidence: 99%