Correspondence-Less Non-rigid Registration of Triangular Surface Meshes

Sánta, Zsolt; Kató, Zoltán

doi:10.1109/cvpr.2013.295

Cited by 12 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, many methods have focused on the problem of registering, or matching, point clouds representing the surface of an entire 3D volume [4,3,40,13,19,25,29]. In this context, a patch-based representation of the surface was also employed in [4].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Nonrigid Surface Registration and Completion from RGBD Images

Salzmann

Wang

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. Nonrigid surface registration is a challenging problem that suffers from many ambiguities. Existing methods typically assume the availability of full volumetric data, or require a global model of the surface of interest. In this paper, we introduce an approach to nonrigid registration that performs on relatively low-quality RGBD images and does not assume prior knowledge of the global surface shape. To this end, we model the surface as a collection of patches, and infer the patch deformations by performing inference in a graphical model. Our representation lets us fill in the holes in the input depth maps, thus essentially achieving surface completion. Our experimental evaluation demonstrates the effectiveness of our approach on several sequences, as well as its robustness to missing data and occlusions.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In the nonrigid case, much of the existing literature has focused on registering volumetric data, where the point clouds represent (the surface of) a full 3D volume (e.g., [4,3,40,13,19,25,29]). Such volumetric data is typically acquired with multiple cameras placed around the scene of interest.…”

Section: Introductionmentioning

confidence: 99%

Nonrigid Surface Registration and Completion from RGBD Images

Salzmann

Wang

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…Unfortunately, neither is directly observable from the scans. What is observable, however, is mesh volume, which is easily computed from the aligned meshes using signed volumes of tetrahedra as described in [Sánta and Kato 2013]. We assume that mesh volume changes result exclusively [Anguelov et al 2005] factors body shape into intrinsic shape and posedependent shape (blue).…”

Section: Data Processingmentioning

confidence: 99%

Breathing life into shape

2014

View full text Add to dashboard Cite

Figure 1: Animating breathing. Here we add realistic breathing shape deformations to a 3D model of a person running. The Euclidean distances between vertices of the breathing and non-breathing model are color coded (red is large, blue is small). Here the runner is breathing mostly with the chest and the temporal pattern of breathing was animated by a "breath actor." AbstractModeling how the human body deforms during breathing is important for the realistic animation of lifelike 3D avatars. We learn a model of body shape deformations due to breathing for different breathing types and provide simple animation controls to render lifelike breathing regardless of body shape. We capture and align high-resolution 3D scans of 58 human subjects. We compute deviations from each subject's mean shape during breathing, and study the statistics of such shape changes for different genders, body shapes, and breathing types. We use the volume of the registered scans as a proxy for lung volume and learn a novel non-linear model relating volume and breathing type to 3D shape deformations and pose changes. We then augment a SCAPE body model so that body shape is determined by identity, pose, and the parameters of the breathing model. These parameters provide an intuitive interface with which animators can synthesize 3D human avatars with realistic breathing motions. We also develop a novel interface for animating breathing using a spirometer, which measures the changes in breathing volume of a "breath actor."

show abstract

“…Our solution is based on the correspondence-less 2D shape registration approach of Domokos et al [2], where non-linear shape deformations are recovered via the solution of a nonlinear system of equations. This method was successfully applied for a number of registration problems in different domains such as volume [20] or medical [15] image registration. In our case, however, the registration has to be done on the spherical surface S, which requires a completely different way to construct equations.…”

Section: Omnidirectional Camera Modelmentioning

confidence: 99%

Relative Pose Estimation and Fusion of Omnidirectional and Lidar Cameras

Tamás

Fröhlich

Kató

2015

Computer Vision - ECCV 2014 Workshops

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a novel approach for the extrinsic parameter estimation of omnidirectional cameras with respect to a 3D Lidar coordinate frame. The method works without specific setup and calibration targets, using only a pair of 2D-3D data. Pose estimation is formulated as a 2D-3D nonlinear shape registration task which is solved without point correspondences or complex similarity metrics. It relies on a set of corresponding regions, and pose parameters are obtained by solving a small system of nonlinear equations. The efficiency and robustness of the proposed method was confirmed on both synthetic and real data in urban environment.

show abstract

Correspondence-Less Non-rigid Registration of Triangular Surface Meshes

Abstract: Abstract

Cited by 12 publications

References 22 publications

Nonrigid Surface Registration and Completion from RGBD Images

Nonrigid Surface Registration and Completion from RGBD Images

Breathing life into shape

Relative Pose Estimation and Fusion of Omnidirectional and Lidar Cameras

Contact Info

Product

Resources

About