(四川大学 计算机学院, 四川 成都 610065;视觉合成图形图像技术国防重点学科实验室(四川大学), 四川 成都 610065)
Face Illumination Transfer Algorithm Based on Intrinsic Images Decomposition
LIU Hao,HU Ke-Xin,LIU Yan-Li
(College of Computer Science, Sichuan University, Chengdu 610065, China;National Key Laboratory of Fundamental Science on Synthetic Vision (Sichuan University), Chengdu 610065, China)
Chart / table
Similar Articles
Article :Browse 1592   Download 1341
Received:May 09, 2014    Revised:August 19, 2014
> 中文摘要: 提出了一种基于本征图像分解的人脸光照迁移算法.首先,针对本征图像分解效果不彻底的情况,提出了一种改进的本征图像分解方法.在此基础上,为了保持人脸细节特征,提出了一种基于边缘保留的光照滤波算法,对参照人脸进行光照迁移至目标人脸,最后融合目标材质图像与滤波后光照图像进行人脸重光照.实验结果表明,与已有算法相比,该算法能够很好地保留迁移后的人脸肤色,并且所生成的重光照效果更准确、自然.
Abstract:In this paper, a face illumination transfer tech based on intrinsic images decomposition is proposed. Firstly, to tackle the issue that the intrinsic image decomposition effect is not perfect, an improved intrinsic image decomposition method is developed. Next, in order to maintain the face feature, a light filtering algorithm based on edge-preserving is created. The algorithm can transfer the illumination from reference face to target face without missing the target details. Finally, the reflectance image and the illumination image are merged to make face relighting. The experimental results show that compared with the existing algorithms, the presented algorithm can preserve the face skin after transfer and the new method produces light effect more reasonable and natural.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61103137);国家科技支撑计划(2012BAH62F02);国家高技术研究发展计划(863)(2013AA013902) 国家自然科学基金(61103137);国家科技支撑计划(2012BAH62F02);国家高技术研究发展计划(863)(2013AA013902)
Foundation items:
Reference text:


LIU Hao,HU Ke-Xin,LIU Yan-Li.Face Illumination Transfer Algorithm Based on Intrinsic Images Decomposition.Journal of Software,2014,25(S2):236-246