Inter-Image Statistics for Scene Reconstruction
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Amodal volume completion: 3D visual completion
Computer Vision and Image Understanding
Inter-Image Statistics for 3D Environment Modeling
International Journal of Computer Vision
Reconstruction of 3D models from intensity images and partial depth
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Amodal volume completion: 3D visual completion
Computer Vision and Image Understanding
Hi-index | 0.00 |
In this paper a range synthesis algorithm is proposedas an initial solution to the problem of 3D environmentmodeling from sparse data. We develop a statistical learningmethod for inferring and extrapolating range data fromas little as one intensity image and from those (sparse) regionswhere both range and intensity information is available.Our work is related to methods for texture synthesisusing Markov Random Field methods. We demonstratethat MRF methods can also be applied to general intensityimages with little associated range information and usedto estimate range values where needed without making anystrong assumptions about the kind of surfaces in the world.Experimental results show the feasibility of our method.