Abstract
This paper is about automatically reconstructing the full 3D surface of an object observed in motion by a single static camera. Based on the two paradigms, structure from motion and linear intensity subspaces, we introduce the geotensity constraint that governs the relationship between four or more images of a moving object. We show that it is possible in theory to solve for 3D Lambertian surface structure for the case of a single point light source and propose that a solution exists for an arbitrary number point light sources. The surface may or may not be textured. We then give an example of automatic surface reconstruction of a face under a point light source using arbitrary unknown object motion and a single fixed camera.
Similar content being viewed by others
References
Beardsley, P.A., Torr, P., and Zisserman, A.P. 1996. 3D model acquisition from extended image sequences. In 4th ECCV, Cambridge, UK, pp. 683–695.
Belhumeur, P.N. and Kriegman, D.J. 1996. What is the set of images of an object under all possible lighting conditions? In CVPR, pp. 270–277.
Devernay, F. and Faugeras, O. 1994. Computing differential properties of 3D shapes from stereoscopic images without 3D models. In CVPR, pp. 208–213.
Epstein, R., Hallinan, P.W., and Yuille, A. 1995. 5 ±2 Eigenimages suffice: An empirical investigation of low-dimensional lighting models. In IEEE Workshop on Physics-Based Modeling in CV, pp. 108–116.
Faugeras, O. 1993. Three-Dimensional Computer Vision. The MIT Press: Cambridge, MA.
Fua, P. 1995. Object-centered surface reconstruction: Combining multi-image stereo and shading. IJCV, 16:35–56.
Horn, B.K.P. 1977. Image intensity understanding. AI, 8:201–231.
Ikeuchi, K. 1981. Determining surface orientation of specular surfaces by using the photometric stereo method. IEEE-PAMI, 3:661–669.
Ikeuchi, K. and Horn, B.K.P. 1981. Numerical shape from shading and occluding boundaries. AI, 17:141–184.
Maki, A., Watanabe, M., and Wiles, C.S. 1998. Geotensity: Combining motion and lighting for 3D surface reconstruction. In 6th ICCV, pp. 1053–1060.
Maki, A. and Wiles, C.S. 2000. Geotensity constraint for 3D surface reconstruction under multiple light sources. In 6th ECCV, pp. 725–741.
Mundy, J.L. and Zisserman, A. (Eds.), 1992. Geometric Invariance in Computer Vision. The MIT Press: Cambridge, MA.
Nayer, S.K. 1990. Determining shape and reflectance of hybrid surfaces by photometric sampling. IEEE Transactions Robotics and Automation, 6:418–431.
Onn, R. and Bruckstein, A. 1990. Integrability disambiguates surface recovery in two-image photometric stereo. IJCV, 5(1):105–431.
Pentland, A.P. 1984. Local shading analysis. IEEE-PAMI, 6:170–187.
Pentland, A.P. 1991. Photometric motion. IEEEE-PAMI, 13(9):879–890.
Seitz, S.M. and Kutulakos, K.N. 1998. Plenoptic image editing. In 6th ICCV, pp. 17–24.
Shashua, A. 1992. Geometry and photometry in 3D visual recognition. Ph.D. Thesis, Dept. Brain and Cognitive Science, MIT.
Tomasi, C. and Kanade, T. 1992. Shape and motion from image streams under orthography: A factorization method. IJCV, 9(2):137–154.
Weinshall, D. and Tomasi, C. 1993. Linear and incremental acquisition of invariant shape models from image sequences. In 4th ICCV, pp. 675–682.
Wiles, C.S., Maki, A., and Matsuda, N. 2001. Hyper-patches for 3D model acquisition and tracking. IEEE-PAMI, 23(12):1391–1403.
Woodham, R.J. 1980. Photometric method for determining surface orientation from multiple images. Optical Engineering, 19:139–144.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Maki, A., Watanabe, M. & Wiles, C. Geotensity: Combining Motion and Lighting for 3D Surface Reconstruction. International Journal of Computer Vision 48, 75–90 (2002). https://doi.org/10.1023/A:1016057422703
Issue Date:
DOI: https://doi.org/10.1023/A:1016057422703