Towards Full 3D Helmholtz Stereovision Algorithms

Amael Delaunoy (1) , Emmanuel Prados (1) , Peter Belhumeur (2)

1 PERCEPTION - Interpretation and Modelling of Images and Videos
2 Department of Computer Science [New York]

Helmholtz stereovision methods are limited to binocular stereovision or depth maps reconstruction. In this paper, we extend these methods to recover the full 3D shape of the objects of a scene from multiview Helmholtz stereopsis. Thus, we are able to reconstruct the complete three-dimensional shape of objects made of any arbitrary and unknown bidirectional reflectance distribution function. Unlike previous methods, this can be achieved using a full surface representation model. In particular occlusions (self occlusions as well as cast shadows) are easier to handle in the surface optimization process. More precisely, we use a triangular mesh representation which allows to naturally specify relationships between the geometry of a point of the scene and its surface normal. We show how to implement the presented approach using a coherent gradient descent flow. Results and benefits are illustrated on various examples.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Amael Delaunoy, Emmanuel Prados, Peter Belhumeur. Towards Full 3D Helmholtz Stereovision Algorithms. ACCV 2007 - 8th Asian Conference on Computer Vision, Nov 2010, Queenstown, New Zealand. pp.39-52, ⟨10.1007/978-3-642-19315-6_4⟩. ⟨inria-00525867⟩