Using 3-dimensional meshes to combine image-based and geometry-based constraints
To recover complicated surfaces, single information sources often prove insufficient. In this paper, we present a unified framework for 3-D shape reconstruction that allows us to combine image-based constraints, such as those deriving from stereo and shape-from-shading, with geometry-based ones, provided here in the form of 3-D points, 3-D features or 2-D silhouettes.
Our approach to shape recovery is to deform a generic object-centered 3-D representation of the surface so as to minimize an objective function. This objective function is a weighted sum of the contributions of the various information sources. We describe these various terms individually, our weighting scheme and our optimization method. Finally, we present results on a number of difficult images of real scenes for which a single source of information would have proved insufficient.
KeywordsObjective Function Geometric Constraint Surface Reconstruction Shape Recovery Laser Range Finder
- [Blake et al., 1985]A. Blake, A. Zisserman, and G. Knowles. Surface descriptions from stereo and shading. Image Vision Computation, 3(4):183–191, 1985.Google Scholar
- [Cryer et al., 1992]J. E. Cryer, Ping-Sing Tsai, and Mubarak Shah. Combining shape from shading and stereo using human vision model. Technical Report CS-TR-92-25, U. Central Florida, 1992.Google Scholar
- [Delingette et al., 1991]H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In Conference on Computer Vision and Pattern Recognition, pages 467–472, 1991.Google Scholar
- [Fua and Leclerc, 1993]P. Fua and Y.G. Leclerc. Object-centered surface reconstruction: Combining multi-image stereo and shading. In ARPA Image Understanding Workshop, Washington, D.C., April 1993.Google Scholar
- [Heipke, 1992]C. Heipke. Integration of digital image matching and multi image shape from shading. In International Society for Photogrammetry and Remote Sensing, pages 832–841, Washington D.C., 1992.Google Scholar
- [Kass et al., 1988]M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, 1(4):321–331, 1988.Google Scholar
- [Leclerc, 1989]Y.G. Leclerc. Constructing simple stable descriptions for image partitioning. International Journal of Computer Vision, 3(1):73–102, 1989.Google Scholar
- [Liedtke et al., 1991]C. E. Liedtke, H. Busch, and R. Koch. Shape adaptation for modelling of 3D objects in natural scenes. In Conference on Computer Vision and Pattern Recognition, pages 704–705, 1991.Google Scholar
- [Szeliski and Tonnesen, 1992]R. Szeliski and D. Tonnesen. Surface modeling with oriented particle systems. In Computer Graphics (SIGGRAPH'92), pages 185–194, July 1992.Google Scholar
- [Terzopoulos and Vasilescu, 1991]D. Terzopoulos and M. Vasilescu. Sampling and reconstruction with adaptive meshes. In Conference on Computer Vision and Pattern Recognition, pages 70–75, 1991.Google Scholar
- [Terzopoulos, 1986]D. Terzopoulos. Regularization of inverse visual problems involving discontinuities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8:413–424, 1986.Google Scholar