Multi-view Shape Modeling from Images: Contributions to Photometric-based Reconstruction using Deformable Meshes

Amaël Delaunoy 1, 2
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Understanding, analyzing and modeling the 3D world from 2D pictures and videos is probably one of the most exciting and challenging problem of computer vision. In this thesis, we address several geometric and photometric aspects to 3D surface reconstruction from multi-view calibrated images. We first formulate multi-view shape reconstruction as an inverse rendering problem. Using generative models, we formulate the problem as an energy minimization method that leads to the non-linear surface optimization of a deformable mesh. A particular attention is addressed to the computation of the discrete gradient flow, which leads to coherent vertices displacements. We particularly focus on models and energy functionals that depend on visibility and photometry. The same framework can then be equally used to perform multi-view stereo, multi-view shape from shading or multi-view photometric stereo. Then, we propose to exploit different additional information to constraint the problem in the non-Lambertian case, where the appearance of the scene depends on the view-point direction. Segmentation for instance can be used to segment surface regions sharing similar appearance or reflectance. Helmholtz reciprocity can also be applied to reconstruct 3D shapes of objects of any arbitrary reflectance properties. By taking multiple image-light pairs around an object, multi-view Helmholtz stereo can be performed. Using this constraint acquisition scenario and our deformable mesh framework, it is possible to reconstruct high quality 3D models.
Liste complète des métadonnées
Contributor : Amaël Delaunoy <>
Submitted on : Wednesday, December 21, 2011 - 10:15:40 AM
Last modification on : Monday, April 9, 2018 - 12:22:27 PM
Document(s) archivé(s) le : Friday, November 16, 2012 - 4:15:45 PM


  • HAL Id : tel-00654188, version 1


Amaël Delaunoy. Multi-view Shape Modeling from Images: Contributions to Photometric-based Reconstruction using Deformable Meshes. Computer Vision and Pattern Recognition [cs.CV]. Université de Grenoble, 2011. English. ⟨tel-00654188v1⟩



Record views


Files downloads