23 June 1993 Combining stereo, shading, and geometric constraints for surface reconstruction from multiple views
Author Affiliations +
Our goal is to reconstruct both the shape and reflectance properties of surfaces from multiple images. We argue that an object-centered representation is most appropriate for this purpose because it naturally accommodates multiple sources of data, multiple images (including motion sequences of a rigid object), self-occlusions, and geometric constraints. We then present a specific object-centered reconstruction method. It begins with an initial estimate of surface shape that is iteratively adjusted to minimize an objective function that combines information from multiple input images. The objective function is a weighted sum of `stereo,' shading, and smoothness components, where the weight varies over the surface. For example, the stereo component is weighted more strongly where the surface projects onto highly textured areas in the images, and less strongly otherwise. Thus, each component has its greatest influence where its accuracy is likely to be greatest. Experimental results on both synthetic and real images are presented.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Pascal Fua, Pascal Fua, Yvan G. Leclerc, Yvan G. Leclerc, } "Combining stereo, shading, and geometric constraints for surface reconstruction from multiple views", Proc. SPIE 2031, Geometric Methods in Computer Vision II, (23 June 1993); doi: 10.1117/12.146618; https://doi.org/10.1117/12.146618


Estimation of projective depths based on genetic algorithm
Proceedings of SPIE (September 24 2001)
Toward accurate and automatic morphing
Proceedings of SPIE (October 24 2005)
Photogrammetric solution for projective reconstruction
Proceedings of SPIE (September 22 1999)
Predictive optical-flow algorithm for aircraft detection
Proceedings of SPIE (October 05 1998)

Back to Top