Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2010 | ACCV (1) | surface optimization process,helmholtz stereovision algorithm,full surface representation model,multiview helmholtz stereopsis,helmholtz stereovision method,coherent gradient descent flow,cast shadow,complete three-dimensional shape,triangular mesh representation,particular occlusion,depth maps reconstruction,three dimensional,bidirectional reflectance distribution function,depth map,triangular mesh,gradient descent |
Field | DocType | Volume |
Bidirectional reflectance distribution function,Computer vision,Gradient descent,Visual hull,Stereopsis,Computer science,Algorithm,Helmholtz free energy,Artificial intelligence,Photometric stereo,Normal,Triangle mesh | Conference | 6492 |
ISSN | Citations | PageRank |
0302-9743 | 9 | 0.50 |
References | Authors | |
23 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Amaël Delaunoy | 1 | 106 | 5.14 |
Emmanuel Prados | 2 | 450 | 20.47 |
Peter N. Belhumeur | 3 | 12242 | 1001.27 |