Data-Driven Synthesis of Cartoon Faces Using Different Styles

Data-Driven Synthesis of Cartoon Faces Using Different Styles
复制标题

使用不同风格的卡通面孔的数据驱动合成

DOI:
10.1109/tip.2016.2628581
复制
发表时间:
2017
影响因子:
10.6
通讯作者:
Deussen Oliver
Deussen Oliver
中科院分区:
计算机科学1区
文献类型:
--
作者:
Zhang Yong;Dong Weiming;Ma Chongyang;Mei Xing;Li Ke;Huang Feiyue;Hu Bao-Gang;Deussen Oliver

文献摘要

参考文献

被引文献

相似文献

本文提出了一种数据驱动的方法,用于从给定的肖像图像自动生成不同风格的卡通面孔。我们的风格化流程包括两个步骤:离线分析步骤,了解如何从数据库中选择和组合面部组件;运行时合成步骤,通过从程式化面部组件数据库中组装部件来生成卡通面部。我们提出了一个优化框架,对于给定的艺术风格,同时考虑面部成分所需的图像卡通关系以及图像构成的适当调整。我们通过图像特征匹配来测量输入图像的面部成分与我们的卡通数据库之间的相似性,并引入一个概率框架来对卡通面部成分之间的关​​系进行建模。我们结合了有关图像-卡通关系的先验知识以及从一组卡通面孔中提取的面部成分的最佳组合,以保持结果的自然、一致和有吸引力的外观。我们通过将其应用于各种肖像图像来展示我们的方法的通用性和稳健性,并将我们的输出与艺术家通过全面的用户研究创建的风格化结果进行比较。
This paper presents a data-driven approach for automatically generating cartoon faces in different styles from a given portrait image. Our stylization pipeline consists of two steps: an offline analysis step to learn about how to select and compose facial components from the databases; a runtime synthesis step to generate the cartoon face by assembling parts from a database of stylized facial components. We propose an optimization framework that, for a given artistic style, simultaneously considers the desired image-cartoon relationships of the facial components and a proper adjustment of the image composition. We measure the similarity between facial components of the input image and our cartoon database via image feature matching, and introduce a probabilistic framework for modeling the relationships between cartoon facial components. We incorporate prior knowledge about image-cartoon relationships and the optimal composition of facial components extracted from a set of cartoon faces to maintain a natural, consistent, and attractive look of the results. We demonstrate generality and robustness of our approach by applying it to a variety of portrait images and compare our output with stylized results created by artists via a comprehensive user study.
DOI: 10.1145/2461912.2461988
发表时间: 2013-07
期刊: ACM Transactions on Graphics (TOG)
影响因子: --
作者:
Sharon Lin;Daniel Ritchie;Matthew Fisher;P. Hanrahan
通讯作者: Sharon Lin;Daniel Ritchie;Matthew Fisher;P. Hanrahan
DOI: 10.1145/2366145.2366153
发表时间: 2012-11
期刊: ACM Transactions on Graphics (TOG)
影响因子: --
作者:
L. Yu;Sai-Kit Yeung;Demetri Terzopoulos;T. Chan
通讯作者: L. Yu;Sai-Kit Yeung;Demetri Terzopoulos;T. Chan
DOI: 10.1109/tip.83
发表时间: 2004
期刊: --
影响因子: --
作者:
通讯作者: --
自动灵活换脸,无需辅助数据
DOI: 10.1016/j.cag.2014.08.001
发表时间: 2014-12
影响因子: 2.5
作者:
Qian Kanglai;Wang Bin;Chen Huarong
通讯作者: Chen Huarong
DOI: 10.1016/j.imavis.2011.11.006
发表时间: 2012
期刊: Image Vis. Comput.
影响因子: --
作者:
Chien-Chung Tseng;J. Lien
通讯作者: Chien-Chung Tseng;J. Lien