Knowledge Commons of Institute of Automation,CAS
Facial-sketch Synthesis: A New Challenge | |
Deng-Ping Fan1; Ziling Huang2; Peng Zheng3; Hong Liu4; Xuebin Qin3; Luc Van Gool1 | |
发表期刊 | Machine Intelligence Research
![]() |
ISSN | 2731-538X |
2022 | |
卷号 | 19期号:4页码:257-287 |
摘要 | This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high cost of obtaining 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 datasets 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 general translation methods, and 35 image-to-sketch approaches. In addition, we elaborate comprehensive experiments on the existing 19 cutting-edge models. Third, we present a simple baseline for FSS, named FSGAN. With only two straightforward components, i.e., facialaware masking and style-vector expansion, our FSGAN surpasses the performance of all previous state-of-the-art models on the proposed FS2K dataset by a large margin. Finally, we conclude with lessons learned over the past years and point out several unsolved challenges. Our code is available at https://github.com/DengPingFan/FSGAN. |
关键词 | Facial sketch synthesis (FSS) facial sketch dataset benchmark attribute style transfer |
DOI | 10.1007/s11633-022-1349-9 |
七大方向——子方向分类 | 其他 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
中文导读 | https://mp.weixin.qq.com/s/jvbcacc-bt_YxPkThTysqA |
视频解析 | https://www.bilibili.com/video/BV1PB4y1675v/ |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/55945 |
专题 | 学术期刊_Machine Intelligence Research |
作者单位 | 1.Computer Vision Laboratory, ETH Zürich, Zürich 8092, Switzerland 2.Information and Communication Engineering, University of Tokyo, Tokyo 113-8654, Japan 3.Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE 4.Digital Content and Media Sciences Research Division, National Institute of Informatics, Tokyo 101-8430, Japan |
推荐引用方式 GB/T 7714 | Deng-Ping Fan,Ziling Huang,Peng Zheng,et al. Facial-sketch Synthesis: A New Challenge[J]. Machine Intelligence Research,2022,19(4):257-287. |
APA | Deng-Ping Fan,Ziling Huang,Peng Zheng,Hong Liu,Xuebin Qin,&Luc Van Gool.(2022).Facial-sketch Synthesis: A New Challenge.Machine Intelligence Research,19(4),257-287. |
MLA | Deng-Ping Fan,et al."Facial-sketch Synthesis: A New Challenge".Machine Intelligence Research 19.4(2022):257-287. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MIR-2022-03-100.pdf(12340KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论