## The correlated correspondence algorithm for unsupervised registration of nonrigid surfaces (2004)

### Cached

### Download Links

Venue: | In TR-SAIL-2004-100, at http://robotics.stanford.edu/∼drago/cc/tr100.pdf |

Citations: | 75 - 4 self |

### BibTeX

@INPROCEEDINGS{Anguelov04thecorrelated,

author = {Dragomir Anguelov and Praveen Srinivasan and Hoi-cheung Pang and Daphne Koller},

title = {The correlated correspondence algorithm for unsupervised registration of nonrigid surfaces},

booktitle = {In TR-SAIL-2004-100, at http://robotics.stanford.edu/∼drago/cc/tr100.pdf},

year = {2004},

pages = {33--40}

}

### Years of Citing Articles

### OpenURL

### Abstract

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 point-topoint 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 real-world datasets, where we demonstrate good results in the presence of significant movement of articulated parts and non-rigid 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 non-rigid object and automatic recovery of articulated object models. 1

### Citations

7048 | Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference - Pearl - 1988 |

2452 | Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography - Fischler, Bolles - 1981 |

2215 |
A method for registration of 3-d shapes
- Besl, McKay
- 1992
(Show Context)
Citation Context ... tasks.s2 Previous Work Surface registration is a fundamental building block in computer graphics. The classical solution for registering rigid surfaces is the Iterative Closest Point algorithm (ICP) =-=[4, 6, 17]-=-. Recently, there has been work extending ICP to non-rigid surfaces [18, 8, 12, 1]. These algorithms treat one of the scans (usually a complete model of the surface) as a deformable template. The link... |

794 | A volumetric method for building complex models from range images - Curless, Levoy - 1996 |

760 | A morphable model for the synthesis of 3d faces
- Blanz, Vetter
- 1999
(Show Context)
Citation Context ...r regions can map to far ones (segment AB) and far regions can map to near ones (points C,D). others assume prior knowledge about the object dynamics [16], or about the space of nonrigid deformations =-=[15, 5]-=-. Algorithms that make neither restriction [18, 12] simplify the problem by decorrelating the choice of correspondences for the different points in the scan. However, this approximation is only good i... |

567 |
Object modeling by registration of multiple range images
- Chen, Medioni
- 1991
(Show Context)
Citation Context ... tasks.s2 Previous Work Surface registration is a fundamental building block in computer graphics. The classical solution for registering rigid surfaces is the Iterative Closest Point algorithm (ICP) =-=[4, 6, 17]-=-. Recently, there has been work extending ICP to non-rigid surfaces [18, 8, 12, 1]. These algorithms treat one of the scans (usually a complete model of the surface) as a deformable template. The link... |

448 | Efficient variants of the icp algorithm
- Rusinkiewicz, Levoy
- 2001
(Show Context)
Citation Context ... tasks.s2 Previous Work Surface registration is a fundamental building block in computer graphics. The classical solution for registering rigid surfaces is the Iterative Closest Point algorithm (ICP) =-=[4, 6, 17]-=-. Recently, there has been work extending ICP to non-rigid surfaces [18, 8, 12, 1]. These algorithms treat one of the scans (usually a complete model of the surface) as a deformable template. The link... |

298 |
Understanding belief propagation and its generalizations
- Yedidia, Freeman, et al.
- 2003
(Show Context)
Citation Context ...espondences, that encodes these geodesic distance constraints as well as penalties for link twisting and stretching, and high-level local surface features [14]. We then apply loopy belief propagation =-=[21]-=- to this model, in order to solve for the entire set of correspondences simultaneously. The result is a registration that respects the surface geometry. To the best of our knowledge, the algorithm we ... |

236 | A new point matching algorithm for non-rigid registration”. Computer Vision and Image Understanding
- Chui, Rangarajan
- 2003
(Show Context)
Citation Context ...n computer graphics. The classical solution for registering rigid surfaces is the Iterative Closest Point algorithm (ICP) [4, 6, 17]. Recently, there has been work extending ICP to non-rigid surfaces =-=[18, 8, 12, 1]-=-. These algorithms treat one of the scans (usually a complete model of the surface) as a deformable template. The links between adjacent points on the surface can be thought of as springs, which are a... |

207 | Fitting smooth surfaces to dense polygon meshes - LEVOY - 1996 |

170 | E.: Construction for Deformable Animated Characters - John, Haumann, et al. - 1989 |

161 | Efficient matching of pictorial structures
- Felzenszwalb, Huttenlocher
- 1973
(Show Context)
Citation Context ... Another line of related work is the work on deformable template matching in the computer vision community. In the 3D case, this framework is used for detection of articulated object models in images =-=[13, 22, 19]-=-. The algorithms assume the decomposition of the object into a relatively small number of parts is known, and that a detector for each object part is available. Template matching approaches have also ... |

138 | Filling holes in complex surfaces using volumetric diffusion
- Davis, Marschner, et al.
- 2002
(Show Context)
Citation Context ...m, wooden puppet and the CAESAR dataset of whole human bodies [1], all acquired by a 3D range scanner. The meshes were not complete surfaces, but several techniques exist for filling the holes (e.g., =-=[10]-=-). We ran the Correlated Correspondence algorithm using the same probabilistic model and the same parameters on all data sets. We use a coarse-to-fine strategy, using the result of a coarse sub-sampli... |

132 | Articulated body deformation from range scan data - Allen, Curless, et al. - 2002 |

119 | Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture
- Cheung, Baker, et al.
(Show Context)
Citation Context ... Fig. 2A. Recovering Articulated Models. Articulated object models have a number of applications in animation and motion capture, and there has been work on recovering them automatically from 3D data =-=[7, 3]-=-. We show that our unsupervised registration capability can greatly assist articulated model recovery. In particular, the algorithm in [3] requires an estimate of the correspondences between a templat... |

114 | Spin-images: A representation for 3-d surface matching
- Johnson
- 1997
(Show Context)
Citation Context ...ne a probabilistic model over the set of correspondences, that encodes these geodesic distance constraints as well as penalties for link twisting and stretching, and high-level local surface features =-=[14]-=-. We then apply loopy belief propagation [21] to this model, in order to solve for the entire set of correspondences simultaneously. The result is a registration that respects the surface geometry. To... |

102 | Spacetime Stereo: A Unifying Framework for Depth from Triangulation - Davis, Nehab, et al. - 2005 |

98 | Finding deformable shapes using loopy belief propagation
- Coughlan, Ferreira
- 2002
(Show Context)
Citation Context ...all number of parts is known, and that a detector for each object part is available. Template matching approaches have also been applied to deformable 2D objects, where very efficient solutions exist =-=[9, 11]-=-. However, these methods do not extend easily to the case of 3D surfaces. 3 The Correlated Correspondence Algorithm The input to the algorithm is a set of two meshes (surfaces tessellated into polygon... |

66 | Unsupervised learning of human motion - Song, Concalves, et al. |

65 | Filling holes in meshes - Liepa - 2003 |

64 | Multi-weight enveloping: least-squares approximation techniques for skin animation - WANG, PHILLIPS |

50 | Attractive People: Assembling Loose-Limbed Models using Non-parametric Belief Propagation
- Sigal, Isard, et al.
- 2003
(Show Context)
Citation Context ... Another line of related work is the work on deformable template matching in the computer vision community. In the 3D case, this framework is used for detection of articulated object models in images =-=[13, 22, 19]-=-. The algorithms assume the decomposition of the object into a relatively small number of parts is known, and that a detector for each object part is available. Template matching approaches have also ... |

40 | S.: Recovering articulated object models from 3D range data
- Anguelov, Koller, et al.
- 2004
(Show Context)
Citation Context ... Fig. 2A. Recovering Articulated Models. Articulated object models have a number of applications in animation and motion capture, and there has been work on recovering them automatically from 3D data =-=[7, 3]-=-. We show that our unsupervised registration capability can greatly assist articulated model recovery. In particular, the algorithm in [3] requires an estimate of the correspondences between a templat... |

36 |
POPOVIĆ J.: Deformation transfer for triangle meshes
- SUMNER
(Show Context)
Citation Context ...lgorithms for deformable surface registration make the problem tractable by assuming significant prior knowledge about the objects being registered. Some rely on the presence of markers on the object =-=[1, 20]-=-, while ∗ A results video is available at http://robotics.stanford.edu/∼drago/cc/video.mp4sFigure 1: A) Registration results for two meshes. Nonrigid ICP and its variant augmented with spin images get... |

33 | An extension of the ICP algorithm for modeling nonrigid objects with mobile robots
- Hähnel, Thrun, et al.
- 2003
(Show Context)
Citation Context ... regions can map to near ones (points C,D). others assume prior knowledge about the object dynamics [16], or about the space of nonrigid deformations [15, 5]. Algorithms that make neither restriction =-=[18, 12]-=- simplify the problem by decorrelating the choice of correspondences for the different points in the scan. However, this approximation is only good in the case when the object deformation is small; ot... |

32 | Morphable Surface Models
- Shelton
- 2000
(Show Context)
Citation Context ... regions can map to near ones (points C,D). others assume prior knowledge about the object dynamics [16], or about the space of nonrigid deformations [15, 5]. Algorithms that make neither restriction =-=[18, 12]-=- simplify the problem by decorrelating the choice of correspondences for the different points in the scan. However, this approximation is only good in the case when the object deformation is small; ot... |

20 |
Statistical models for medical image analysis
- Leventon
- 2000
(Show Context)
Citation Context ...r regions can map to far ones (segment AB) and far regions can map to near ones (points C,D). others assume prior knowledge about the object dynamics [16], or about the space of nonrigid deformations =-=[15, 5]-=-. Algorithms that make neither restriction [18, 12] simplify the problem by decorrelating the choice of correspondences for the different points in the scan. However, this approximation is only good i... |

11 | Tracking articulated objects in realtime range image sequences
- Lin
- 1999
(Show Context)
Citation Context ...ormation potentials can violate mesh geometry. Near regions can map to far ones (segment AB) and far regions can map to near ones (points C,D). others assume prior knowledge about the object dynamics =-=[16]-=-, or about the space of nonrigid deformations [15, 5]. Algorithms that make neither restriction [18, 12] simplify the problem by decorrelating the choice of correspondences for the different points in... |

10 | Representation and Detection of Shapes in Images
- Felzenszwalb
- 2003
(Show Context)
Citation Context ...all number of parts is known, and that a detector for each object part is available. Template matching approaches have also been applied to deformable 2D objects, where very efficient solutions exist =-=[9, 11]-=-. However, these methods do not extend easily to the case of 3D surfaces. 3 The Correlated Correspondence Algorithm The input to the algorithm is a set of two meshes (surfaces tessellated into polygon... |

6 |
Concurrent object recognition and segmentation with graph partitioning
- Yu, Gross, et al.
- 2002
(Show Context)
Citation Context ... Another line of related work is the work on deformable template matching in the computer vision community. In the 3D case, this framework is used for detection of articulated object models in images =-=[13, 22, 19]-=-. The algorithms assume the decomposition of the object into a relatively small number of parts is known, and that a detector for each object part is available. Template matching approaches have also ... |

2 | Face recognition based on 3d shape estimation from single images - Blanz, Vetter - 2002 |

1 |
The space of human body shapes:reconstruction and parameterization from range scans
- Allen, Curless, et al.
- 2003
(Show Context)
Citation Context ...lgorithms for deformable surface registration make the problem tractable by assuming significant prior knowledge about the objects being registered. Some rely on the presence of markers on the object =-=[1, 20]-=-, while ∗ A results video is available at http://robotics.stanford.edu/∼drago/cc/video.mp4sFigure 1: A) Registration results for two meshes. Nonrigid ICP and its variant augmented with spin images get... |

1 | A new signature-based method for efiicient 3-d object recognition - RUIZ-CORREA, SHAPIRO, et al. - 2001 |