Abstract
This paper focuses on recovering the 3D structure and motion of human faces from a sequence of 2D images. Based on a probabilistic model, we extensively studied the rotation constraints of the problem. Instead of imposing numerical optimizations, the inherent geometric properties of the rotation matrices are taken into account. The conventional Newton’s method for optimization problems was generalized on the rotation manifold, which ultimately resolves the constraints into unconstrained optimization on the manifold. Furthermore, we also extended the algorithm to model within-individual and between-individual shape variances separately. Evaluation results give evidence to the improvement over the state-of-the-art algorithms on the Mocap-Face dataset with additive noise, as well as on the Binghamton University A 3D Facial Expression (BU-3DFE) dataset. Robustness in handling noisy data and modeling multiple subjects shows the capability of our system to deal with real-world image tracks.
Original language | English |
---|---|
Article number | 45 |
Pages (from-to) | 1-12 |
Number of pages | 12 |
Journal | Eurasip Journal on Image and Video Processing |
Volume | 2015 |
Issue number | 1 |
DOIs | |
Publication status | Published - 1 Dec 2015 |
Bibliographical note
Publisher Copyright:© 2015, Qu et al.
Funding
This work was done when H. Gao was at Computer Vision for Human-Computer Interaction Lab (CV:HCI), Karlsruhe Institute of Technology (KIT). H. K. Ekenel was partially supported by TUBITAK, project no. 113E121 and a Marie Curie FP7 Integration Grant within the 7 EU Framework Programme. We acknowledge support by Deutsche Forschungsgemeinschaft (DFG) and Open Access Publishing Fund of KIT. th
Funders | Funder number |
---|---|
Deutsche Forschungsgemeinschaft | |
Seventh Framework Programme | |
TUBITAK | 113E121 |
Karlsruhe Institute of Technology | |
Seventh Framework Programme | |
Deutsche Forschungsgemeinschaft |
Keywords
- Face model
- Manifold optimization
- Newton’s method
- Non-rigid structure from motion
- PLDA