Reliable feature matching across widely separated views

By Adam Baumberg. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000

780 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/67f693427d956c0dbc822e7f3452aee8ca36204b

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

SURF: Speeded Up Robust Features (2006, methodology): “An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants [17], complex features [18, 19], steerable filters [20], phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interest poi”
Scale & Affine Invariant Interest Point Detectors (2004, positive): “The affine shape estimation was used for matching and recognition by Baumberg (2000).”
3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints (2006, neutral): “…constraints exploited in that case are usually related to the distance between matching points and the corresponding epipolar lines (Pritchett and Zisserman, 1998; Schaffalitzky and Zisserman, 2002; Baumberg, 2000; Tell and Carlsson, 2000; Matas et al., 2002; Tuytelaars and Van Gool, 2004).”
Scale Invariant Feature Transform on the Sphere: Theory and Applications (2011, background): “A wide variety of local descriptors has also been proposed in the literature (Zabih and Woodﬁll 1994; Van Gool et al. 1996; Baumberg 2000; Lowe 2004; Mikolajczyk and Schmid 2005).”
Local feature view clustering for 3D object recognition (2001, background): “Baumberg [1] has developed a local feature descriptor that incorporates local affine invariance with r otation invariant Fourier descriptors.”
ASIFT: A New Framework for Fully Affine Invariant Image Comparison (2009, background): “The necessity of considering high transition tilts is illustrated in Figure 8.”
A performance evaluation of local descriptors (2005, background): “However, in this representation the spatial relations between points are not explicit and the basis functions are in(cid:2)nite, therefore dif(cid:2)cult to adapt to a local approach.”
Robust wide-baseline stereo from maximally stable extremal regions (2004, methodology): “Baumberg [1] applied an iterative scheme originally proposed by Lindeberg and Gårding [6] to associate affineinvariant measurement regions with Harris interest points.”
A SIFT descriptor with global context (2005, background): “There has been a lot of other work in detecting, describing , and matching feature points [1] [12] [15] [19] [20].”
Modeling the World from Internet Photo Collections (2008, background): “…use a quasicontinuous sampling of scale space to detect points invariant to changes in scale and orientation (Lowe 2004; Mikolajczyk and Schmid 2004) and somewhat invariant to affine transformations (Baumberg 2000; Kadir and Brady 2001; Schaffalitzky and Zisserman 2002; Mikolajczyk et al. 2005).”
Unsupervised 3D object recognition and reconstruction in unordered datasets (2005, methodology): “By using descriptors that are invariant not just to translation, but also to rotation [16], scale [9] and affine warping [3, 12, 11], invariant features provide much more robust matching than previous correlation based methods.”
Invariant Features from Interest Point Groups (2002, methodology): “Results show that dense feature matching can be achieved in a few seconds of computation on 1GHz Pentium III machines.”
Computer Vision - ECCV 2004 (2004, methodology): “It does not hold for non-coplanar triples in presence of strong parallax in a few cases, coined parallax-violations [1].”
A Comparison of Affine Region Detectors (2005, background): “These regions have been used in quite varied applications including: wide baseline matching for stereo pairs [1, 21, 31, 47], reconstructing cameras for sets of disparate views [34], image retrieval from large databases [36, 45], model based recognition [7, 18, 29, 32], object retrieval in video…”
Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?" (2002, methodology): “Consequently we will require wide baseline matching methods [2, 10, 12, 11, 15, 16, 18, 21, 23, 24] to compute multiview relations.”
Distinctive Image Features from Scale-Invariant Keypoints (2004, methodology): “Therefore, we have used an approximate algorithm, called the Best-Bin-First (BBF) algorithm (Beis and Lowe, 1997).”
The structure-from-motion reconstruction pipeline - a survey with focus on short image sequences (2010, methodology): “It provides the option to compute affinely invariant image patches as in [1].”