Biphasic Face Photo-Sketch Synthesis via Semantic-Driven Generative Adversarial Network with Graph Representation Learning

01/05/2022
by   Xingqun Qi, et al.
4

In recent years, significant progress has been achieved in biphasic face photo-sketch synthesis with the development of Generative Adversarial Network (GAN). Biphasic face photo-sketch synthesis could be applied in wide-ranging fields such as digital entertainment and law enforcement. However, generating realistic photos and distinct sketches suffers from great challenges due to the low quality of sketches and complex photo variations in the real scenes. To this end, we propose a novel Semantic-Driven Generative Adversarial Network to address the above issues, cooperating with the Graph Representation Learning. Specifically, we inject class-wise semantic layouts into the generator to provide style-based spatial supervision for synthesized face photos and sketches. In addition, to improve the fidelity of the generated results, we leverage the semantic layouts to construct two types of Representational Graphs which indicate the intra-class semantic features and inter-class structural features of the synthesized images. Furthermore, we design two types of constraints based on the proposed Representational Graphs which facilitate the preservation of the details in generated face photos and sketches. Moreover, to further enhance the perceptual quality of synthesized images, we propose a novel biphasic training strategy which is dedicated to refine the generated results through Iterative Cycle Training. Extensive experiments are conducted on CUFS and CUFSF datasets to demonstrate the prominent ability of our proposed method which achieves the state-of-the-art performance.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 9

research
06/29/2021

Face Sketch Synthesis via Semantic-Driven Generative Adversarial Network

Face sketch synthesis has made significant progress with the development...
research
10/27/2017

High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks

Synthesizing face sketches from real photos and its inverse are well stu...
research
10/12/2018

Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis

Face sketch-photo synthesis is a critical application in law enforcement...
research
06/22/2018

KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network

In this paper, we propose a kinship generator network that can synthesiz...
research
05/09/2020

Quality Guided Sketch-to-Photo Image Synthesis

Facial sketches drawn by artists are widely used for visual identificati...
research
10/04/2017

Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Sketch portrait generation benefits a wide range of applications such as...
research
11/11/2019

PoshakNet: Framework for matching dresses from real-life photos using GAN and Siamese Network

Online garment shopping has gained many customers in recent years. Descr...

Please sign up or login with your details

Forgot password? Click here to reset