Using 3-Dimensional Meshes To Combine Image-Based and Geometry-Based Constraints

A uni ed framework for 3 D shape reconstruction allows us to combine image-based and geometry-based information sources. The image information is akin to stereo and shape-fromshading, while the geometric information may be provided in the form of 3 D points, 3 D features or 2 D silhouettes. A formalintegration framework is critical in recovering complicated surfaces because the information from a single source is often insu cient to provide a unique answer. 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 optimizationmethod. Finally,we present results on a number of di cult images of real scenes for which a single source of information would have proved insu cient. Keywords : Surface reconstruction, Stereo, Shape-from-s...

• Type: Conference
• Year: 1994
• Where: ECCV
• Authors: Pascal Fua, Yvan G. Leclerc
• Keywords: Computer Vision, ECCV 1994, Insu Cient, Objective Function, Shape Reconstruction, Uni Ed Framework, Various Information Sources