Facial-sketch Synthesis: A New Challenge

doi:10.1007/s11633-022-1349-9

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Facial-sketch Synthesis: A New Challenge
	Deng-Ping Fan 4
刊名	Machine Intelligence Research
	2022
卷号	19 页码:257-287
关键词	Facial sketch synthesis (FSS) facial sketch dataset benchmark attribute style transfer
ISSN号	2731-538X
DOI	10.1007/s11633-022-1349-9
英文摘要	This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high cost of ob taining hand-drawn sketch datasets, there is a lack of a complete benchmark for assessing the development of FSS algorithms over the last decade. We first introduce a high-quality dataset for FSS, named FS2K, which consists of 2104 image-sketch pairs spanning three types of sketch styles, image backgrounds, lighting conditions, skin colors, and facial attributes. FS2K differs from previous FSS data sets in difficulty, diversity, and scalability and should thus facilitate the progress of FSS research. Second, we present the largest-scale FSS investigation by reviewing 89 classic methods, including 25 handcrafted feature-based facial-sketch synthesis approaches, 29 gener al translation methods, and 35 image-to-sketch approaches. In addition, we elaborate comprehensive experiments on the existing 19 cut ting-edge models. Third, we present a simple baseline for FSS, named FSGAN. With only two straightforward components, i.e., facial aware masking and style-vector expansion, our FSGAN surpasses the performance of all previous state-of-the-art models on the pro posed FS2K dataset by a large margin. Finally, we conclude with lessons learned over the past years and point out several unsolved chal lenges. Our code is available at https://github.com/DengPingFan/FSGAN.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49642]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	1.Digital Content and Media Sciences Research Division, National Institute of Informatics, Tokyo 101-8430, Japan 2.Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE 3.Information and Communication Engineering, University of Tokyo, Tokyo 113-8654, Japan 4.Computer Vision Laboratory, ETH Zürich, Zürich 8092, Switzerland
推荐引用方式 GB/T 7714	Deng-Ping Fan. Facial-sketch Synthesis: A New Challenge[J]. Machine Intelligence Research,2022,19:257-287.
APA	Deng-Ping Fan.(2022).Facial-sketch Synthesis: A New Challenge.Machine Intelligence Research,19,257-287.
MLA	Deng-Ping Fan."Facial-sketch Synthesis: A New Challenge".Machine Intelligence Research 19(2022):257-287.