iccv iccv2013 iccv2013-302 iccv2013-302-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Georgios Tzimiropoulos, Maja Pantic
Abstract: We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-ofthe-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at ht tp ://ibug. . doc . i . a c . uk/resources. c
[1] S. Baker, R. Gross, and I. Matthews. Lucas-kanade 20 years on: Part 3. Robotics Institute, Carnegie Mellon University, Tech. Rep. CMU-RI-TR-03-35, 2003.
[2] A. U. Batur and M. H. Hayes. Adaptive active appearance models. IEEE TIP, 14(1 1): 1707–1721, 2005.
[3] P. Belhumeur, D. Jacobs, D. Kriegman, and N. Kumar. Localizing parts of faces using a consensus of exemplars. In CVPR, 2011.
[4] S. Boyd and L. Vandenberghe. Convex optimization. Cam-
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15]
[16] bridge university press, 2004. T. Cootes, G. Edwards, and C. Taylor. Active appearance models. IEEE TPAMI, 23(6):681–685, 2001. D. Cristinacce and T. Cootes. Feature detection and tracking with constrained local models. In BMVC, 2006. R. Gross, I. Matthews, and S. Baker. Generic vs. person specific active appearance models. Image and Vision Computing, 23(12): 1080–1093, 2005. R. Gross, I. Matthews, J. Cohn, T. Kanade, and S. Baker. Multi-pie. Image and Vision Computing, 28(5):807–813, 2010. G. D. Hager and P. N. Belhumeur. Efficient region tracking with parametric models of geometry and illumination. IEEE TPAMI, 20(10):1025–1039, 1998. V. Le, J. Brandt, Z. Lin, L. Bourdev, and T. S. Huang. Interactive facial feature localization. In ECCV. 2012. X. Liu. Generic face alignment using boosted appearance model. In CVPR, 2007. D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91–1 10, 2004. B. D. Lucas, T. Kanade, et al. An iterative image registration technique with an application to stereo vision. In 7th International Joint Conference on Artificial Intelligence, 1981 . S. Lucey, R. Navarathna, A. Ashraf, and S. Sridharan. Fourier lucas-kanade algorithm. IEEE TPAMI, 35(6): 1383– 1396, 2013. P. Martins, R. Caseiro, and J. Batista. Generative face alignment through 2.5 d active appearance models. CVIU, 2012. I. Matthews and S. Baker. Active appearance models revisited. IJCV, 60(2): 135–164, 2004.
[17] K. Netzell and J. E. Solem. Efficient image inner products applied to active appearance models. In ICPR, 2008.
[18] G. Papandreou and P. Maragos. Adaptive and constrained algorithms for inverse compositional active appearance model fitting. In CVPR, 2008.
[19] C. Sagonas, G. Tzimiropoulos, S. Zafeiriou, and M. Pantic. A semi-automatic methodology for facial landmark annotation. In CVPR Workshops, 2013.
[20] J. Saragih and R. Gocke. Learning aam fitting through simulation. Pattern Recognition, 42(1 1):2628–2636, 2009.
[21] J. Saragih and R. Goecke. A nonlinear discriminative approach to aam fitting. In ICCV, 2007.
[22] H. Wu, X. Liu, and G. Doretto. Face alignment via boosted ranking model. In CVPR, 2008.
[23] J. Xiao, S. Baker, I. Matthews, and T. Kanade. Real-time combined 2d+3d active appearance models. In CVPR, 2004.
[24] X. Zhu and D. Ramanan. Face detection, pose estimation, and landmark estimation in the wild. In CVPR, 2012. 600