iccv iccv2013 iccv2013-219 iccv2013-219-reference knowledge-graph by maker-knowledge-mining

219 iccv-2013-Internet Based Morphable Model


Source: pdf

Author: Ira Kemelmacher-Shlizerman

Abstract: In thispaper wepresent a new concept ofbuilding a morphable model directly from photos on the Internet. Morphable models have shown very impressive results more than a decade ago, and could potentially have a huge impact on all aspects of face modeling and recognition. One of the challenges, however, is to capture and register 3D laser scans of large number of people and facial expressions. Nowadays, there are enormous amounts of face photos on the Internet, large portion of which has semantic labels. We propose a framework to build a morphable model directly from photos, the framework includes dense registration of Internet photos, as well as, new single view shape reconstruction and modification algorithms.


reference text

[1]

[2]

[3]

[4]

[5]

[6] Frgc (face recognition grand challenge) by nist. 1 http://make3d.cs.cornell.edu/. 2, 6 http://www.facegen.com/. 2, 6 http://www.image-metrics.com/. 2, 5, 6, 8 http://www.vizago.ch/. 2, 6, 8 O. Alexander, M. Rogers, W. Lambeth, J.-Y. Chiang, W.-C. Ma, C.-C. Wang, and P. Debevec. The digital emily project: Achieving a photorealistic digital actor. IEEE Computer Graphics and Applications, 30:20–3 1, 2010. 2

[7] J. T. Barron and J. Malik. Shape, albedo, and illumination from a single image of an unknown object. CVPR, 2012. 2

[8] R. Basri, D. Jacobs, and I. Kemelmacher. Photometric stereo with general, unknown lighting. International Journal of Computer Vision, pages 239–257, 2007. 2

[9] R. Basri, D. Jacobs, and I. Kemelmacher. Photometric stereo with general, unknown lighting. International Journal of Computer Vision, 72(3):239–257, 2007. 4, 5 33225614 ?????????? ????? ????? ????????? ????? ????? ????? ????????? ????? identity, pose, lighting, etc.

[10] R. Basri and D. W. Jacobs. Lambertian reflectance and linear subspaces. PAMI, 25(2):218–233, 2003. 4

[11] T. Beeler, B. Bickel, P. Beardsley, B. Sumner, and M. Gross. High-quality single-shot capture of facial geometry. ACM Trans. on Graphics (Proc. SIGGRAPH), 29(3), 2010. 2

[12] P. N. Belhumeur, D. J. Kriegman, and A. L. Yuille. The basrelief ambiguity. International Journal of Computer Vision, 35(1):33–44, 1999. 5

[13] V. Blanz and T. Vetter. A morphable model for the synthesis of 3d faces. In SIGGRAPH, pages 187–194, 1999. 1, 2

[14] D. Bradley, W. Heidrich, T. Popa, and A. Sheffer. High resolution passive facial performance capture. ACM Trans. on Graphics (Proc. SIGGRAPH), 29(3), 2010. 2

[15] C. Bregler, A. Hertzmann, and H. Biermann. Recovering non-rigid 3d shape from image streams. In CVPR, 2000. 4

[16] J. M. Buenaposada Biencinto, E. Mu˜ noz, and L. Baumela Molina. A model of brightness variations due to illumination changes and non-rigid motion using spherical harmonics. 2008. 4

[17] A. Georghiades, P. Belhumeur, and D. Kriegman. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE PAMI, 2001 . 6

[18] H. Hayakawa. Photometric stereo under a light source with

[19]

[20]

[21]

[22]

[23]

[24]

[25]

[26]

[27]

[28] arbitrary motion. JOSA A, 11(11):3079–3089, 1994. 2, 4 K. Karsch, C. Liu, and S. B. Kang. Depth extraction from video using non-parametric sampling. In ECCV, 2012. 2, 6 I. Kemelmacher-Shlizerman and R. Basri. 3d face reconstruction from a single image using a single reference face shape. IEEE PAMI, 2010. 2, 6, 8 I. Kemelmacher-Shlizerman and S. M. Seitz. Face reconstruction in the wild. In ICCV, 2011. 2, 4, 5 I. Kemelmacher-Shlizerman and S. M. Seitz. Collection flow. In CVPR, pages 1792–1799, 2012. 3, 4 C. Liu. Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. PhD thesis, MIT, 2009. 4 T.Hassner and R. Basri. Example based 3d reconstruction from single 2d images. In Beyond Patches Workshop CVPR, 2006. 2 T. Weise, B. Leibe, and L. V. Gool. Fast 3d scanning with automatic motion compensation. In CVPR, June 2007. 2 R. J. Woodham. Multiple light source optical ow. ICCV, page 4246, 1990. 4, 6 L. Zhang, N. Snavely, B. Curless, and S. M. Seitz. Spacetime faces: high resolution capture for modeling and animation. In SIGGRAPH, pages 548–558, 2004. 2 S. K. Zhou, R. Chellappa, and D. W. Jacobs. Characterization of human faces under illumination variations using rank, integrability, and symmetry constraints. In Computer VisionECCV 2004, pages 588–601. Springer, 2004. 4 33225625 ????? ???? ???? Figure6.Comparisont [20]onYaleBdatse.?W e? u?se? ex?actly the same measure as in Fig.7 of [20] and show several typical reconstructions on this dataset compared to calibrated photometric stereo (known lighting). We get comparable results, typical reconstruction error in [20] is around 6 − 7% while ours in typically s4t%ru.c ????? ????? ????? ??????? ?????? Figure7.Typicalreconstructionwithmorphablemodelmethods [5, 4] on baby pictures. The shape does not account for facial expressions, and looks close to the average person model (note the profile views of the reconstruction). Compare with Figure 4 that includes our results. 33225636