3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints

DOI10.1007/s11263-005-3674-1zbMath1477.68418OpenAlexW2059412355MaRDI QIDQ2508353

Jean Ponce, Svetlana Lazebnik, Fred Rothganger, Cordelia Schmid

Publication date: 12 October 2006

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://hal.inria.fr/inria-00548618/file/rothganger_ijcv_final.pdf

zbMATH Keywords

multi-view geometryimage-based modelingaffine-invariant image descriptorsthree-dimensional object recognition

Mathematics Subject Classification ID

Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Machine vision and scene understanding (68T45)

Related Items (12)

Affine equivalences of trigonometric curves ⋮ Familiarity based unified visual attention model for fast and robust object recognition ⋮ 3D model comparison using spatial structure circular descriptor ⋮ Keypoints and local descriptors of scalar functions on 2D manifolds ⋮ A robust feature matching approach for photography originality test ⋮ Affine-invariant curvature estimators for implicit surfaces ⋮ Scale-free registrations in 3D: 7 degrees of freedom with Fourier Mellin SOFT transforms ⋮ Temporal scale selection in time-causal scale space ⋮ Dense Scale Selection Over Space, Time, and Space-Time ⋮ 3D object recognition using invariants of 2D projection curves ⋮ A computational theory of visual receptive fields ⋮ Image matching using generalized scale-space interest points

Uses Software

• SIFT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Application of invariance in computer vision. 2nd Joint European - US Workshop, Ponta Delgada, Azores, Portugal, October 9-14, 1993. Proceedings
• Probabilistic models of appearance for 3-D object recognition
• The combinatorics of object recognition in cluttered environments using constrained search
• Computer Vision - ECCV 2004
• Computer Vision - ECCV 2004
• Saliency, scale and image description

This page was built for publication: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints