飞人：利用基灵矢量场的图像高保真变形.pdfVIP

第28 卷 第 8 期 计算机辅助设计与图形学学报 Vol. 28 No.8 2016 年8 月 Journal of Computer-Aided Design Computer Graphics Aug. 2016 飞人: 利用基灵矢量场的图像高保真变形 1) 1) 1) 2) 杜振龙 , 赵中武 , 李晓丽 , 郭延文 1) (南京工业大学计算机科学与技术学院 南京 211816) 2) (南京大学计算机软件新技术国家重点实验室 南京 210023) (duzhl@) : 为了把常态实拍人物图像参考指定姿态变形为跳、飞奔、飞跃的“飞人”效果, 提出一种利用基灵矢量场 的图像高保真变形方法. 该方法利用改进的 GrabCut 算法提取待变形的目标人物; 通过语义骨架匹配算法把人物骨 架与姿态模板骨架进行匹配; 利用骨架约束基灵矢量场实现图像变形, 从而达到实拍常态人物图像变形为跳、飞奔、 飞跃等效果. 实验结果表明, 文中方法能够处理人物图像间的变形, 有效地把人物图像参照姿态模板进行变形, 效果 真实. ：图像变形; 基灵矢量场; 保真; 骨架语义匹配 ：TP391.41 Flying People: High-fidelity Image Warping via Killing Vector Fields Du Zhenlong1), Zhao Zhongwu1), Li Xiaoli1) and Guo Yanwen2) 1) (School of Computer Science Technology, Nanjing TECH University, Nanjing 211816) 2) (State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023) Abstract: For realistically warping one real people image with reference to another template gesture so as to make the stand people jump, hop, or skip, etc., a method of high-fidelity image warping via Killing vector fields (KVF) is proposed, which employs the improved GrabCut algorithm for object extraction, exploits the semantic skeleton match approach for aligning the skeleton, and makes use of the constrained KVF warping image for jump, hop, or skip, etc. Experiments demonstrate that the presented method could warp the images with less relevance, and high-fidelity warp one stand people with reference to different gesture. Key words: image warping; Killing vector fields; high-fidelity; semantic skeleton match , . [1-4], . , ,