Detailed 3D Face Reconstruction from Single Images Via Self-supervised Attribute Learning

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 三维可视计算

	Detailed 3D Face Reconstruction from Single Images Via Self-supervised Attribute Learning
	Mingxin, Yang1,2 ; Jianwei, Guo1,2 ; Juntao, Ye1 ; Xiaopeng, Zhang1,2
	2020-12
会议名称	ACM SIGGRAPH Asia
会议日期	12.4-12.13
会议地点	线上
出版者	Association for Computing Machinery
摘要	We present a novel approach to reconstruct high-fidelity geometric human face model from a single RGB image. The main idea is to add details into a coarse 3D Morphable Model (3DMM) based model in a self-supervised way. Our observation is that most of the facial details like wrinkles are driven by expression and intrinsic facial characteristics which here we refer to as the facial attribute. To this end, we propose an expression related details recovery scheme and a facial attribute representation.
关键词	3D Face Reconstruction 3DMM Face Attribute Learning
收录类别	EI
语种	英语
七大方向——子方向分类	计算机图形学与虚拟现实
国重实验室规划方向分类	视觉信息处理
是否有论文关联数据集需要存交	否
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/44888
专题	多模态人工智能系统全国重点实验室_三维可视计算
作者单位	1.NLPR, CASIA 2.School of AI, Univ. of CAS
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Mingxin, Yang,Jianwei, Guo,Juntao, Ye,et al. Detailed 3D Face Reconstruction from Single Images Via Self-supervised Attribute Learning[C]:Association for Computing Machinery,2020.

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
3415264.3425455.pdf（617KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载