Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions

By Tinne Tuytelaars, Luc Van Gool. British Machine Vision Conference, 2000

580 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9ad20e6f6f89631caf6960516bb9939b9430bba0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Class-Based Feature Matching Across Unrestricted Transformations (2008, background): “Several popular schemes [2], [3], [4], [15] work with socalled affine invariants.”
SuperGlue: Learning Feature Matching With Graph Neural Networks (2019, methodology): “The classical pipeline developed in the 2000s is often based on SIFT [28], filters matches with Lowe’s ratio test [28], the mutual check, and heuristics such as neighborhood consensus [53, 9, 5, 45], and finds a transformation with a robust solver like RANSAC [19, 40].”
Evaluation of Features Detectors and Descriptors based on 3D Objects (2005, methodology): “To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically.”
ASIFT: A New Framework for Fully Affine Invariant Image Comparison (2009, unknown): “Some moment-based region detectors [24, 3] including the Harris-affine and Hessianaffine region detectors [35, 37], an edge-based region detector [58, 57], an intensity-based region detector [56, 57], an entropy-based region detector [18], and two level line-based region detectors, MSER (“maximally ”
Invariant Features from Interest Point Groups (2002, background): “Results show that dense feature matching can be achieved in a few seconds of computation on 1GHz Pentium III machines.”
World-scale mining of objects and events from community photo collections (2008, background): “First, more powerful (local) visual features [3, 14, 15, 16, 30] have led to signiﬁcant progress in recognition capabilities, both for speciﬁc objects [27] and for object classes [7, 12, 24].”
A performance evaluation of local descriptors (2005, methodology): “The idea is to detect image regions covariant to a class of transformations, which are then used as support regions to compute invariant descriptors.”
Video data mining using configurations of viewpoint invariant regions (2004, background): “The objective of this work is to extract significant objects, characters and scenes in a video by determining the frequency of occurrence of spatial configurations.”
Maximally Stable Colour Regions for Recognition and Matching (2007, methodology): “These frames are covariant with image changes under either a similarity transform (translation, scale, and rotation) [7, 15], or an affine transform (also includes skew and different scalings of axes) [5, 8, 10, 14].”
On Space-Time Interest Points (2005, unknown): “Highly successful applications of interest points have been presented for image indexing (Schmid and Mohr, 1997), stereo matching (Tuytelaars and Van Gool, 2000; Mikolajczyk and Schmid, 2002; Tell and Carlsson, 2002), optic ﬂow estimation and tracking (Smith and Brady, 1995; Bretzner and Lindeberg,…”
An Affine Invariant Interest Point Detector (2002, methodology): “Tuytelaars and Van Gool [16] detect affine invariant regions based on image intensities.”
Multi-image matching using multi-scale oriented patches (2005, background): “Other researchers have developed feature descriptors that are invariant under affine transformations [7, 8, 9].”
View-Invariant Recognition Using Corresponding Object Fragments (2004, methodology): “To represent sub-parts in an invariant manner, one approach has been to use affine-invariant patches [3, 2 ].”