ABSTRACT
This paper proposes a novel face texture mapping framework for 3D face reconstruction from a single frontal view or half-profile view facial image. Face reconstruction method that originates from the proposed framework, unlike most of the existing ones, is novel in the sense that it is not tightly coupled to a specific face model, and yet it simplifies the pose estimation problem which is pivotal to the success of face reconstruction. This paper details the proposed framework, and illustrates how it addresses the ill-posed pose estimation problem, of which the solution is optimal in the least square sense. With accurate pose estimation of face, precise texture mapping is thus made possible to allow photo realistic rendering of face images in the 3D space. Experimental results demonstrates that reliable and photo realistic 3D face reconstruction can be easily realized in our framework by utilizing a generic 3D face model, standard Haar-like feature based detector and active appearance model. With proposed frame work, face recognition systems could be more robust to pose changes by reconstructing frontal faces from non-frontal ones.
- K. M. Lam and H. Yan, "An analytic-to-holistic approach for face recognition based on a single frontal view", IEEE Trans. on PAMI, vol. 20, pp. 673--686, 1998. Google ScholarDigital Library
- V. Blanz and T. Vetter, "Face recognition based on fitting a 3D morphable model", IEEE Trans. on PAMI, vol. 25, pp. 1063--1074, 2003. Google ScholarDigital Library
- Y. Hu, D. Jiang, S. Yan, L. Zhang, and H. Zhang, "Automatic 3D reconstruction for face recognition", Proc. of IEEE Conf. on AFGR, pp 843--848, 2004. Google ScholarDigital Library
- T. F. Cootes, K. Walker, and C. J. Taylor, "View-based active appearance models", Proc. of IEEE AFGR, pp 227--232, 2000. Google ScholarDigital Library
- S. W. Park, J. Heo, and M. Savvides, "3D face reconstruction from a single 2D face image", presented at IEEE Conf. on CVPR Workshops, pp 1--8, 2008.Google Scholar
- R. Lienhart and J. Maydt, "An extended set of Haar-like features for rapid object detection", Proc. of IEEE ICIP, vol. 1, pp 900--903, 2002.Google ScholarCross Ref
- T. F. Cootes, G. J. Edwards, and C. J. Taylor, "Active appearance models", IEEE Trans. on PAMI, vol. 23, pp. 681--685, 2001. Google ScholarDigital Library
- Z. Zhang, Y. Hu, T. Yu, and T. Huang, "Minimum variance estimation of 3D face shape from multi-view", Proc. of IEEE Conf. on AFGR, pp 547--552, 2006. Google ScholarDigital Library
- F. Tarres and A. Rama, "GTAV Face Database", available at http://gps-tsc.upc.es/GTAV/ResearchAreas/UPCFaceDatabase/GTAVFaceDatabase.htmGoogle Scholar
- "The Facial Recognition Technology (FERET) Database", http://www.itl.nist.gov/iad/humanid/feret/feret_master.htmlGoogle Scholar
Index Terms
- Automatic 3D face texture mapping framework from single image
Recommendations
Super-Resolution of Faces Using Texture Mapping on a Generic 3D Model
ICIG '09: Proceedings of the 2009 Fifth International Conference on Image and GraphicsThis paper proposes a novel face texture mapping framework to transform faces with different poses into a unique texture map. Under this framework, texture mapping can be realized by utilizing a generic 3D face model, standard Haar-like feature based ...
Single 2D Image-based 3D Face Reconstruction and Its Application in Pose Estimation
Fundamentals of Knowledge TechnologyHuman beings are born with a natural capacity of recovering shape from merely one image. However, it is still a challenging mission for current techniques to make a computer have such an ability. To simulate the modeling procedure of human visual system,...
Single 2D Image-based 3D Face Reconstruction and Its Application in Pose Estimation
Fundamentals of Knowledge TechnologyHuman beings are born with a natural capacity of recovering shape from merely one image. However, it is still a challenging mission for current techniques to make a computer have such an ability. To simulate the modeling procedure of human visual system,...
Comments