TY - JOUR
T1 - 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints
AU - Rothganger, Fred
AU - Lazebnik, Svetlana
AU - Schmid, Cordelia
AU - Ponce, Jean
N1 - Funding Information:
This research was partially supported by the National Science Foundation under grants IIS-0308087 and IIS-0312438, Toyota Motor Corporation, the UIUC-CNRS Research Collaboration Agreement, the European FET-open project VIBES, the UIUC Campus Research Board, and the Beckman Institute. We would like to thank V. Ferrari, M. Hebert, D. Lowe, S. Mahamud, M. Maire, P. Moreels, M. Munich, P.
PY - 2006/3
Y1 - 2006/3
N2 - This article introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between the corresponding surface patches. Geometric constraints associated with different views of the same patches under affine projection are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true 3D affine and Euclidean models from multiple unregistered images, as well as their recognition in photographs taken from arbitrary viewpoints. The proposed approach does not require a separate segmentation stage, and it is applicable to highly cluttered scenes. Modeling and recognition results are presented.
AB - This article introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between the corresponding surface patches. Geometric constraints associated with different views of the same patches under affine projection are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true 3D affine and Euclidean models from multiple unregistered images, as well as their recognition in photographs taken from arbitrary viewpoints. The proposed approach does not require a separate segmentation stage, and it is applicable to highly cluttered scenes. Modeling and recognition results are presented.
KW - Affine-invariant image descriptors
KW - Image-based modeling
KW - Multi-view geometry
KW - Three-dimensional object recognition
UR - http://www.scopus.com/inward/record.url?scp=33644508026&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33644508026&partnerID=8YFLogxK
U2 - 10.1007/s11263-005-3674-1
DO - 10.1007/s11263-005-3674-1
M3 - Review article
AN - SCOPUS:33644508026
VL - 66
SP - 231
EP - 259
JO - International Journal of Computer Vision
JF - International Journal of Computer Vision
SN - 0920-5691
IS - 3
ER -