Sciweavers

Share
CVPR
2003
IEEE

3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints

9 years 9 months ago
3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints
: This paper presents a novel representation for three-dimensional objects in terms of affine-invariant image patches and their spatial relationships. Multi-view constraints associated with groups of patches are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true three-dimensional affine and Euclidean models from multiple images and their recognition in a single photograph taken from an arbitrary viewpoint. The proposed approach does not require a separate segmentation stage and is applicable to cluttered scenes. Preliminary modeling and recognition results are presented.
Fred Rothganger, Svetlana Lazebnik, Cordelia Schmi
Added 12 Oct 2009
Updated 29 Oct 2009
Type Conference
Year 2003
Where CVPR
Authors Fred Rothganger, Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
Comments (0)
books