Filters








9,751 Hits in 3.0 sec

The Correlated Correspondence Algorithm for Unsupervised Registration of Nonrigid Surfaces

Dragomir Anguelov, Praveen Srinivasan, Hoi-Cheung Pang, Daphne Koller, Sebastian Thrun, James Davis
2004 Neural Information Processing Systems  
We present an unsupervised algorithm for registering 3D surface scans of an object undergoing significant deformations.  ...  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.  ...  Our results show that the algorithm can deal with articulated objects subject to large joint movements, as well as with non-rigid surface deformations.  ... 
dblp:conf/nips/AnguelovSPKTD04 fatcat:5l3qyywoxjfq5dy6walahxhnoy

Coregistration: Simultaneous Alignment and Modeling of Articulated 3D Shape [chapter]

David A. Hirshberg, Matthew Loper, Eric Rachlin, Michael J. Black
2012 Lecture Notes in Computer Science  
By minimizing a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model.  ...  To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan.  ...  Hasler for use of the human body scan dataset and A. Tsoli and J. Purmort for their help with mesh registration.  ... 
doi:10.1007/978-3-642-33783-3_18 fatcat:t6agmva2tvbt7k7pi2gchttskq

Scan-Based Volume Animation Driven by Locally Adaptive Articulated Registrations

Taehyun Rhee, J P Lewis, U Neumann, K Nayak
2011 IEEE Transactions on Visualization and Computer Graphics  
This paper describes a complete system to create anatomically accurate example-based volume deformation and animation of articulated body regions, starting from multiple in vivo volume scans of a specific  ...  Our registration step establishes a correspondence across scans, allowing a data-driven deformation approach in the volume domain.  ...  a locally smooth deformation adaptively and cumulatively over a hierarchy of scales.  ... 
doi:10.1109/tvcg.2010.39 pmid:21233517 fatcat:te47lyultfejjcowlra5utwqju

Dynamic Cage-Driven 3D Range-Scan Alignment [article]

Lee M. Seversky, Lijun Yin
2010 Eurographics State of the Art Reports  
This paper presents a novel and automatic approach for aligning range-scan data of objects exhibiting non-rigid, articulated motion using a cage-driven reduced deformable model.  ...  data of objects exhibiting non-rigid, articulated motion using a cage-driven reduced deformable model.  ...  This work addresses the registration problem for range-scan data of non-rigid articulated real world objects.  ... 
doi:10.2312/egsh.20101056 fatcat:ryrlzv7pxvh6nd423ptykog2w4

Robust single-view geometry and motion reconstruction

Hao Li, Bart Adams, Leonidas J. Guibas, Mark Pauly
2009 ACM SIGGRAPH Asia 2009 papers on - SIGGRAPH Asia '09  
input scans reconstruction input scans reconstruction input scans reconstruction Figure 1 : Reconstruction of complex deforming objects from high-resolution depth scans.  ...  Large-scale motion of the acquired object is recovered using a novel space-time adaptive, non-rigid registration method.  ...  Template registration uses a nonlinear reduced deformable model to recover the large-scale motion and align the template to each of the input scans (Section 4).  ... 
doi:10.1145/1661412.1618521 fatcat:2hjvqwdkaja2vpclq2dd3lowm4

3D Menagerie: Modeling the 3D Shape and Pose of Animals

Silvia Zuffi, Angjoo Kanazawa, David W. Jacobs, Michael J. Black
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We learn an articulated, 3D, statistical shape model of animals using very little training data.  ...  Consequently, we learn our model from a small set of 3D scans of toy figurines in arbitrary poses. We employ a novel partbased shape model to compute an initial registration to the scans.  ...  We thank Seyhan Sitti for scanning the toys and Federica Bogo and Javier Romero for their help with the silhouette term. AK and DJ were supported by the National Science Foundation under grant no.  ... 
doi:10.1109/cvpr.2017.586 dblp:conf/cvpr/ZuffiKJB17 fatcat:sdpzz4ho7vhklfozwuc7kzez4y

Robust single-view geometry and motion reconstruction

Hao Li, Bart Adams, Leonidas J. Guibas, Mark Pauly
2009 ACM Transactions on Graphics  
input scans reconstruction input scans reconstruction input scans reconstruction Figure 1 : Reconstruction of complex deforming objects from high-resolution depth scans.  ...  Large-scale motion of the acquired object is recovered using a novel space-time adaptive, non-rigid registration method.  ...  Template registration uses a nonlinear reduced deformable model to recover the large-scale motion and align the template to each of the input scans (Section 4).  ... 
doi:10.1145/1618452.1618521 fatcat:zxu5j7ymqvav7gwwbf5vwmezwi

3D Menagerie: Modeling the 3D shape and pose of animals [article]

Silvia Zuffi, Angjoo Kanazawa, David Jacobs, Michael J. Black
2017 arXiv   pre-print
There has been significant work on learning realistic, articulated, 3D models of the human body. In contrast, there are few such models of animals, despite many applications.  ...  Consequently, we learn our model from a small set of 3D scans of toy figurines in arbitrary poses. We employ a novel part-based shape model to compute an initial registration to the scans.  ...  We thank Seyhan Sitti for scanning the toys and Federica Bogo and Javier Romero for their help with the silhouette term. AK and DJ were supported by the National Science Foundation under grant no.  ... 
arXiv:1611.07700v2 fatcat:voftoalqtrejzjtbcztu5ljp5a

Dynamic Geometry Registration [article]

Niloy J. Mitra, Simon Floery, Maks Ovsjanikov, Natasha Gelfand, Leonidas Guibas, Helmut Pottmann
2007 Symposium on geometry processing : [proceedings]. Symposium on Geometry Processing  
We propose an algorithm that performs registration of large sets of unstructured point clouds of moving and deforming objects without computing correspondences.  ...  We demonstrate the performance of our algorithm on a number of synthetic and scanned examples, each consisting of hundreds of scans.  ...  This better preserves articulated parts of the scanned object.  ... 
doi:10.2312/sgp/sgp07/173-182 fatcat:jqarwunz6naqzassmswbpw2l5y

SCAPE-based human performance reconstruction

Jiaxiang Zheng, Ming Zeng, Xuan Cheng, Xinguo Liu
2014 Computers & graphics  
a SCAPE model based on an expanded human pose database containing human poses collected from different databases to enlarge the tracking space, (2) develop a correspondence estimation method based on articulated  ...  Also thanks to Yangzi Ding for the scanning data. This work was partially supprted by NSFC (No. 61379068).  ...  However, our reconstruction is only for human performance and we can choose a more robust pose tracking and transferring method for the large scale pose deformation; and due to the noisy scanning data,  ... 
doi:10.1016/j.cag.2013.10.023 fatcat:puhbh3w2zjhnxo3qsihku7ubia

Reconstructing the past: methods and techniques for the digital restoration of fossils

Stephan Lautenschlager
2016 Royal Society Open Science  
(a) Articulated braincase of Stegosaurus stenops in dorsal view showing plastic deformation.  ...  Taking into account that plastic deformation can occur non-uniformly or together with brittle deformation, retrodeformation, in particular, of three-dimensional objects, might not only introduce a large  ... 
doi:10.1098/rsos.160342 pmid:27853548 pmcid:PMC5098973 fatcat:an4snxreurgzxitmnuv2r4tfhi

Shape Correspondence with Isometric and Non-Isometric Deformations

R. M. Dyke, C. Stride, Y.-K. Lai, P. L. Rosin, M. Aubry, A. Boyarski, A. M. Bronstein, M. M. Bronstein, D. Cremers, M. Fisher, T. Groueix, D. Guo (+14 others)
2019 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
In this paper, we capture a benchmark dataset of scanned 3D shapes undergoing various controlled deformations (articulating, bending, stretching and topologically changing), along with ground truth correspondences  ...  The registration of surfaces with non-rigid deformation, especially non-isometric deformations, is a challenging problem.  ...  Conclusions In this paper we have presented a novel dataset of real-world scanned objects that cover a large variety of deformation types.  ... 
doi:10.2312/3dor.20191069 fatcat:uaiihsrxinadlcerh7wqhx65ie

GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models

Hongyi Xu, Eduard Gabriel Bazavan, Andrei Zanfir, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Given high-resolution complete 3D body scans of humans, captured in various poses, together with additional closeups of their head and facial expressions, as well as hand articulation, and given initial  ...  We present a statistical, articulated 3D human shape modeling pipeline, within a fully trainable, modular, deep learning framework.  ...  Hence, inevitably, they did not take advantage of the large scale data analysis and model construction process that recently emerged in the context of deep learning.  ... 
doi:10.1109/cvpr42600.2020.00622 dblp:conf/cvpr/XuBZFSS20 fatcat:52hilf2kh5hbzh72whlvj5jdc4

Temporally coherent completion of dynamic shapes

Hao Li, Linjie Luo, Daniel Vlasic, Pieter Peers, Jovan Popović, Mark Pauly, Szymon Rusinkiewicz
2012 ACM Transactions on Graphics  
Because of occlusions and low surface albedo, scanned mesh sequences typically exhibit large holes that persist over extended periods of time.  ...  Consequently, our method does not suffer from error accumulation typically introduced by noise, large deformations, and drastic topological changes.  ...  Bi-resolution approaches presented by Ahmed et al. [2008] and Li et al. [2009] deform a smooth template to match large-scale motion to scanned geometry of a dynamic performance.  ... 
doi:10.1145/2077341.2077343 fatcat:pwpdh6mpibcwrn57r4joauq4km

Simultaneous correspondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images

Eduard Serradell, Adriana Romero, Ruben Leta, Carlo Gatta, Francesc Moreno-Noguer
2011 2011 International Conference on Computer Vision  
As a result, and in contrast to existing approaches that assume rigidity or quasi-rigidity of the structure, our method is able to retrieve large non-linear deformations even when the input data is corrupted  ...  of occlusions and allowing to retrieve large deformations.  ...  As shown in Fig. 3 these covariances are set to relatively large values in order to deal with different types of deformations.  ... 
doi:10.1109/iccv.2011.6126325 dblp:conf/iccv/SerradellRLGM11 fatcat:zjbaanpq6bgl3n3zecrjzplwm4
« Previous Showing results 1 — 15 out of 9,751 results