Skip to Main content Skip to Navigation
New interface
Conference papers

Joint Feature Distributions for Image Correspondence

Bill Triggs 1 
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We introduce `Joint Feature Distributions', a general statistical framework for feature based multi-image matching that explicitly models the joint probability distributions of corresponding features across several images. Conditioning on feature positions in some of the images gives well-localized distributions for their correspondents in the others, and hence tight likelihood regions for correspondence search. We apply the framework in the simplest case of Gaussian-like distributions over the direct sum (affine images) and tensor product (projective images) of the image coordinates. This produces probabilistic correspondence models that generalize the geometric multi-image matching constraints, roughly speaking by a form of model-averaging over them. These very simple methods predict accurate correspondence likelihood regions for any scene geometry including planar and near-planar scenes, without ill-conditioning or explicit model selection. Small amounts of distortion and non-rigidity are also tolerated. We develop the theory for any number of affine or projective images, explain its relationship to matching tensors, and give results for an initial implementation.
Document type :
Conference papers
Complete list of metadata
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Monday, December 20, 2010 - 8:42:37 AM
Last modification on : Friday, February 4, 2022 - 3:31:57 AM
Long-term archiving on: : Thursday, June 30, 2011 - 1:44:52 PM




Bill Triggs. Joint Feature Distributions for Image Correspondence. 8th International Conference on Computer Vision (ICCV '01), Jul 2001, Vancouver, Canada. pp.201--208, ⟨10.1109/ICCV.2001.937625⟩. ⟨inria-00548272⟩



Record views


Files downloads