Face Hallucination Using Split-Attention in Split-Attention Network

10/22/2020
by   Yuanzhi Wang, et al.
0

Face hallucination is a domain-specific super-resolution (SR), that generates high-resolution (HR) facial images from the observed one/multiple low-resolution (LR) input/s. Recently, convolutional neural networks(CNNs) are successfully applied into face hallucination to model the complex nonlinear mapping between HR and LR images. Although global attention mechanism equipped into CNNs naturally focus on the facial structure information, it always ignore the local and cross feature structure information, resulting in limited reconstruction performance. In order to solve this problem, we propose global-local split-attention mechanism and design a Split-Attention in Split-Attention (SIS) network to enable local attention across feature-map groups attaining global attention and to improve the ability of feature representations. SIS can generate and focus the local attention of neural network on the interaction of face key structure information in channel-level, thereby improve the performance of face image reconstruction. Experimental results show that the proposed approach consistently and significantly improves the reconstruction performances for face hallucination.

READ FULL TEXT

page 4

page 9

research
12/22/2019

Joint Face Super-Resolution and Deblurring Using a Generative Adversarial Network

Facial image super-resolution (SR) is an important preprocessing for fac...
research
09/16/2021

TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network

Recently, face super-resolution (FSR) methods either feed whole face ima...
research
04/08/2020

Image super-resolution reconstruction based on attention mechanism and feature fusion

Aiming at the problems that the convolutional neural networks neglect to...
research
04/01/2020

Feature-Driven Super-Resolution for Object Detection

Although some convolutional neural networks (CNNs) based super-resolutio...
research
12/08/2020

Hierarchical Residual Attention Network for Single Image Super-Resolution

Convolutional neural networks are the most successful models in single i...
research
05/04/2019

Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning

Face hallucination is a domain-specific super-resolution problem that ai...
research
08/10/2017

Attention-Aware Face Hallucination via Deep Reinforcement Learning

Face hallucination is a domain-specific super-resolution problem with th...

Please sign up or login with your details

Forgot password? Click here to reset