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 developme...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.展开更多
The digitalization software developed based on AutoCAD is one important platform of GIS data gather. But because AutoCAD itself is not the software of GIS, it can not be used to collect the attribute data. And convers...The digitalization software developed based on AutoCAD is one important platform of GIS data gather. But because AutoCAD itself is not the software of GIS, it can not be used to collect the attribute data. And conversion data to GIS software often lose some information such as color, line style, symbol shape. By using the XDATA, the Handle, the Group of AutoCAD and the provided ObjectArx to Redevelop, under AutoCAD condition, the attribute information collection with space information were realized, also did the AutoCAD symbol integrity and accurate expresses, then the demand of the digit graphics was satisfied.展开更多
基金supported by the Grant-in-Aid for Japan Society for the Promotion of Science Fellows, Japan (No. 21F50377)
文摘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.
文摘The digitalization software developed based on AutoCAD is one important platform of GIS data gather. But because AutoCAD itself is not the software of GIS, it can not be used to collect the attribute data. And conversion data to GIS software often lose some information such as color, line style, symbol shape. By using the XDATA, the Handle, the Group of AutoCAD and the provided ObjectArx to Redevelop, under AutoCAD condition, the attribute information collection with space information were realized, also did the AutoCAD symbol integrity and accurate expresses, then the demand of the digit graphics was satisfied.
基金山东省自然科学基金(the Natural Science Foundation of Shandong Province of China under Grant No.Y2004A04)山东省科学发展计划项目(the Science Development Plan of Shandong Province of China under Grant No.B2006053)
