Results 1  10
of
247
Shape matching and object recognition using low distortion correspondence
 In CVPR
, 2005
"... We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of correspond ..."
Abstract

Cited by 307 (13 self)
 Add to MetaCart
We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of corresponding geometric blur point descriptors as well as the geometric distortion between pairs of corresponding feature points. The algorithm handles outliers, and thus enables matching of exemplars to query images in the presence of occlusion and clutter. Given the correspondences, we estimate an aligning transform, typically a regularized thin plate spline, resulting in a dense correspondence between the two shapes. Object recognition is then handled in a nearest neighbor framework where the distance between exemplar and query is the matching cost between corresponding points. We show results on two datasets. One is the Caltech 101 dataset (FeiFei, Fergus and Perona), an extremely challenging dataset with large intraclass variation. Our approach yields a 48 % correct classification rate, compared to FeiFei et al’s 16%. We also show results for localizing frontal and profile faces that are comparable to special purpose approaches tuned to faces. 1.
Shape Context and Chamfer Matching in Cluttered Scenes
, 2003
"... This paper compares two methods for object localization from contours: shape context and chamfer matching of templates. In the light of our experiments, we suggest improvements to the shape context: Shape contexts are used to find corresponding features between model and image. In real images it is ..."
Abstract

Cited by 99 (6 self)
 Add to MetaCart
This paper compares two methods for object localization from contours: shape context and chamfer matching of templates. In the light of our experiments, we suggest improvements to the shape context: Shape contexts are used to find corresponding features between model and image. In real images it is shown that the shape context is highly influenced by clutter, furthermore even when the object is correctly localized, the feature correspondence may be poor. We show that the robustness of shape matching can be increased by including a figural continuity constraint. The combined shape and continuity cost is minimized using the Viterbi algorithm on features sequentially around the contour, resulting in improved localization and correspondence. Our algorithm can be generally applied to any feature based shape matching method.
The correlated correspondence algorithm for unsupervised registration of nonrigid surfaces
 In TRSAIL2004100, at http://robotics.stanford.edu/∼drago/cc/tr100.pdf
, 2004
"... We present an unsupervised algorithm for registering 3D surface scans of an object undergoing significant deformations. Our algorithm does not need markers, nor does it assume prior knowledge about object shape, the dynamics of its deformation, or scan alignment. The algorithm registers two meshes b ..."
Abstract

Cited by 76 (4 self)
 Add to MetaCart
We present an unsupervised algorithm for registering 3D surface scans of an object undergoing significant deformations. Our algorithm does not need markers, nor does it assume prior knowledge about object shape, the dynamics of its deformation, or scan alignment. The algorithm registers two meshes by optimizing a joint probabilistic model over all pointtopoint correspondences between them. This model enforces preservation of local mesh geometry, as well as more global constraints that capture the preservation of geodesic distance between corresponding point pairs. The algorithm applies even when one of the meshes is an incomplete range scan; thus, it can be used to automatically fill in the remaining surfaces for this partial scan, even if those surfaces were previously only seen in a different configuration. We evaluate the algorithm on several realworld datasets, where we demonstrate good results in the presence of significant movement of articulated parts and nonrigid surface deformation. Finally, we show that the output of the algorithm can be used for compelling computer graphics tasks such as interpolation between two scans of a nonrigid object and automatic recovery of articulated object models. 1
Surface matching via currents
 IPMI 2005. LNCS
, 2005
"... Abstract. We present a new method for computing an optimal deformation between two arbitrary surfaces embedded in Euclidean 3dimensional space. Our main contribution is in building a norm on the space of surfaces via representation by currents of geometric measure theory. Currents are an appropriat ..."
Abstract

Cited by 67 (1 self)
 Add to MetaCart
Abstract. We present a new method for computing an optimal deformation between two arbitrary surfaces embedded in Euclidean 3dimensional space. Our main contribution is in building a norm on the space of surfaces via representation by currents of geometric measure theory. Currents are an appropriate choice for representations because they inherit natural transformation properties from differential forms. We impose a Hilbert space structure on currents, whose norm gives a convenient and practical way to define a matching functional. Using this Hilbert space norm, we also derive and implement a surface matching algorithm under the large deformation framework, guaranteeing that the optimal solution is a onetoone regular map of the entire ambient space. We detail an implementation of this algorithm for triangular meshes and present results on 3D face and medical image data. 1
Möbius voting for surface correspondence
 ACM TRANS. GRAPH. (PROC. SIGGRAPH
, 2009
"... The goal of our work is to develop an efficient, automatic algorithm for discovering point correspondences between surfaces that are approximately and/or partially isometric. Our approach is based on three observations. First, isometries are a subset of the Möbius group, which has lowdimensionality ..."
Abstract

Cited by 62 (4 self)
 Add to MetaCart
The goal of our work is to develop an efficient, automatic algorithm for discovering point correspondences between surfaces that are approximately and/or partially isometric. Our approach is based on three observations. First, isometries are a subset of the Möbius group, which has lowdimensionality – six degrees of freedom for topological spheres, and three for topological discs. Second, computing the Möbius transformation that interpolates any three points can be computed in closedform after a midedge flattening to the complex plane. Third, deviations from isometry can be modeled by a transportationtype distance between corresponding points in that plane. Motivated by these observations, we have developed a Möbius Voting algorithm that iteratively: 1) samples a triplet of three random points from each of two point sets, 2) uses the Möbius transformations defined by those triplets to map both point sets into a canonical coordinate frame on the complex plane, and 3) produces “votes” for predicted correspondences between the mutually closest points with magnitude representing their estimated deviation from isometry. The result of this process is a fuzzy correspondence matrix, which is converted to a permutation matrix with simple matrix operations and output as a discrete set of point correspondences with confidence values. The main advantage of this algorithm is that it can find intrinsic point correspondences in cases of extreme deformation. During experiments with a variety of data sets, we find that it is able to find dozens of point correspondences between different object types in different poses fully automatically.
Using the InnerDistance for Classification of Articulated Shapes
 In Proc. CVPR
, 2005
"... We propose using the innerdistance between landmark points to build shape descriptors. The innerdistance is defined as the length of the shortest path between landmark points within the shape silhouette. We show that the innerdistance is articulation insensitive and more effective at capturing com ..."
Abstract

Cited by 57 (9 self)
 Add to MetaCart
We propose using the innerdistance between landmark points to build shape descriptors. The innerdistance is defined as the length of the shortest path between landmark points within the shape silhouette. We show that the innerdistance is articulation insensitive and more effective at capturing complex shapes with part structures than Euclidean distance. To demonstrate this idea, it is used to build a new shape descriptor based on shape contexts. After that, we design a dynamic programming based method for shape matching and comparison. We have tested our approach on a variety of shape databases including an articulated shape dataset, MPEG7 CEShape1, Kimia silhouettes, a Swedish leaf database and a human motion silhouette dataset. In all the experiments, our method demonstrates effective performance compared with other algorithms. 1
Nonrigid point set registration: Coherent Point Drift (CPD)
 IN ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 19
, 2006
"... We introduce Coherent Point Drift (CPD), a novel probabilistic method for nonrigid registration of point sets. The registration is treated as a Maximum Likelihood (ML) estimation problem with motion coherence constraint over the velocity field such that one point set moves coherently to align with ..."
Abstract

Cited by 56 (0 self)
 Add to MetaCart
We introduce Coherent Point Drift (CPD), a novel probabilistic method for nonrigid registration of point sets. The registration is treated as a Maximum Likelihood (ML) estimation problem with motion coherence constraint over the velocity field such that one point set moves coherently to align with the second set. We formulate the motion coherence constraint and derive a solution of regularized ML estimation through the variational approach, which leads to an elegant kernel form. We also derive the EM algorithm for the penalized ML optimization with deterministic annealing. The CPD method simultaneously finds both the nonrigid transformation and the correspondence between two point sets without making any prior assumption of the transformation model except that of motion coherence. This method can estimate complex nonlinear nonrigid transformations, and is shown to be accurate on 2D and 3D examples and robust in the presence of outliers and missing points.
BRealtime nonrigid surface detection
 in Proc. IEEE Conf. Computer Vision Pattern Recognition
, 2005
"... We present a realtime method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches between an undeformed image of the object and the image in which it is to be detected. The matches are used not only to de ..."
Abstract

Cited by 51 (5 self)
 Add to MetaCart
We present a realtime method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches between an undeformed image of the object and the image in which it is to be detected. The matches are used not only to detect but also to compute a precise mapping from one to the other. The algorithm is robust to large deformations, lighting changes, motion blur, and occlusions. It runs at 10 frames per second on a 2.8 GHz PC and we are not aware of any other published technique that produces similar results. Introducing deformable meshes, along with a well designed robust estimator, is the key to dealing with the large number of parameters involved in modeling deformable surfaces and rejecting erroneous matches for error rates of up to 95%, which is considerably more than what is required in practice. 1
Diffeomorphic matching of distributions: A new approach for unlabelled pointsets and submanifolds matching
 In CVPR (pp. 712–718). Los Alamitos: IEEE Comput. Soc
, 2004
"... In the paper, we study the problem of optimal matching of two generalized functions (distributions) via a diffeomorphic transformation of the ambient space. In the particular case of discrete distributions (weighted sums of Dirac measures), we provide a new algorithm to compare two arbitrary unlabel ..."
Abstract

Cited by 49 (7 self)
 Add to MetaCart
In the paper, we study the problem of optimal matching of two generalized functions (distributions) via a diffeomorphic transformation of the ambient space. In the particular case of discrete distributions (weighted sums of Dirac measures), we provide a new algorithm to compare two arbitrary unlabelled sets of points, and show that it behaves properly in limit of continuous distributions on submanifolds. As a consequence, the algorithm may apply to various matching problems, such as curve or surface matching (via a subsampling), or mixings of landmark and curve data. As the solution forbids high energy solutions, it is also robust towards addition of noise and the technique can be used for nonlinear projection of datasets. We present 2D and 3D experiments. 1.
An Extension of the ICP Algorithm for Modeling Nonrigid Objects with Mobile Robots
"... The iterative closest point (ICP) algorithm [2] is a popular method for modeling 3D objects from range data. The classical ICP algorithm rests on a rigid surface assumption. Building on recent work on nonrigid object models [5, 16, 9] , this paper presents an ICP algorithm capable of modeling nonrig ..."
Abstract

Cited by 35 (5 self)
 Add to MetaCart
The iterative closest point (ICP) algorithm [2] is a popular method for modeling 3D objects from range data. The classical ICP algorithm rests on a rigid surface assumption. Building on recent work on nonrigid object models [5, 16, 9] , this paper presents an ICP algorithm capable of modeling nonrigid objects, where individual scans may be subject to local deformations. We describe an integrated mathematical framework for simultaneously registering scans and recovering the surface configuration. To tackle the resulting...