Yasuhiro Akagi
ABSTRACT
We propose a key point detection and refinement method for a facial motion tracking and transfer. Since key-point-based approaches for representing facial expressions usually deform faces by interpolating movements of the key points, the approaches cause errors between the deformed face and the original one. To solve this problem, our method tracks non-rigid deformations of surfaces to detects additional key points for minimizing the errors.
Supplemental Material
- Cao, X., Wei, Y., Wen, F., and Sun, J. 2012. Face alignment by explicit shape regression. In CVPR, IEEE, 2887--2894. Google Scholar
Digital Library
- Jian, B., and Vemuri, B. C. 2011. Robust point set registration using gaussian mixture models. IEEE Trans. Pattern Anal. Mach. Intell. 33, 8 (aug), 1633--1645. Google ScholarDigital Library
- Sumner, R. W., Schmid, J., and Pauly, M. 2007. Embedded deformation for shape manipulation. In ACM SIGGRAPH 2007 papers, ACM, SIGGRAPH '07. Google ScholarDigital Library
Index Terms
A facial tracking and transfer method with a key point refinement
Recommendations
Extracting Realistic 3D Facial Animation Parameters from Multiview Video Clips
In this article, an accurate and inexpensive procedure to estimate 3D facial and lip motion trajectories from mirror-reflected multi-view video clips is proposed. Two planar mirrors are located near a subject's cheeks, and a single camera is utilized to ...
Facial Landmark Detection and Tracking for Facial Behavior Analysis
ICMR '16: Proceedings of the 2016 ACM on International Conference on Multimedia RetrievalThe face is the most dominant and distinct communication tool of human beings. Automatic analysis of facial behavior allows machines to understand and interpret a human's states and needs for natural interactions. This research focuses on developing ...
From 2D to 3D real-time expression transfer for facial animation
In this paper, we present a three-stage approach, which creates realistic facial animations by tracking expressions of a human face in 2D and transferring them to a human-like 3D model in real-time. Our calibration-free method, which is based on an ...
Comments