3-D Shape Reconstruction from Stereovision Data Using Object-Consisted Markov Random Field Model
Neural Information Processing
Scene modelling from sparse 3D data
Image and Vision Computing
3D shape recovery by the use of single image plus simple pattern illumination
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Shape from incomplete silhouettes based on the reprojection error
Image and Vision Computing
Nonstructured light-based sensing for 3D reconstruction
Pattern Recognition
Mesh optimisation using edge information in feature-based surface reconstruction
ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part I
Manifold surface reconstruction of an environment from sparse Structure-from-Motion data
Computer Vision and Image Understanding
| Hi-index | 0.00 |
This paper describes an approach to recovering surface models ofcomplex scenes from the quasi-sparse data returned by a featurebased stereo system. The method can be used to merge stereo resultsobtained from different viewpoints into a single coherent surfacemesh. The technique proceeds by exploiting the free space theoremwhich provides a principled mechanism for reasoning about thestructure of the scene based on quasi-sparse correspondences inmultiple image. Effective methods for overcoming the difficultiesposed by missing features and outliers are discussed. Resultsobtained by applying this approach to actual images are presented.