Articulated body deformation from range scan data

By Brett Allen, Brian Curless, Zoran Popovic. International Conference on Computer Graphics and Interactive Techniques, 2002

396 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/ae549e7685a3e02f86c9afee75add71fdd32d984

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Skinning mesh animations (2005, methodology): “2000] comprises one such family of approaches wherein character shapes (or local frame corrections) are interpolated as a function of character pose (see also [Allen et al. 2002]).”
Learning an efficient model of hand shape variation from depth images (2015, methodology): “[3] represent the model as an adaptation of a standard subdivision surface model with linear blend skinning.”
Skinning with dual quaternions (2007, methodology): “Several methods successfully exploit modern motion capture and/or 3D scanning devices to capture skin deformation of real people [Allen et al. 2002; Anguelov et al. 2005; Park and Hodgins 2006; Allen et al. 2006].”
Gesture recognition for human-robot collaboration: A review (2017, methodology): “With the bene ﬁ ts mentioned above, the skeleton model approach has become an attractive solution for depth sensors (Han et al., 2013; Li, 2012).”
Articulated mesh animation from multi-view silhouettes (2008, methodology): “To learn a skinning model, Allen et al. [2002] obtain corresponded shapes for different poses by matching a subdivision surface template to range data.”
Real-time 3D model acquisition (2002, background): “Acquisition of deformable models would be especially attractive for capturing human animation [Allen et al. 2002].”
Building efficient, accurate character skins from examples (2003, methodology): “Another recent work applies these techniques to range scan data [Allen et al. 2002].”
3D-CODED: 3D Correspondences by Deep Deformation (2018, background): “While such template-based techniques provide the best correspondence results they require a careful parameterization of the template, which took more than a decade of research to reach the current level of maturity [1,2,3,25,49].”
SCAPE: shape completion and animation of people (2005, methodology): “Given a set of markers between two meshes, the task of non-rigid registration is well understood and a variety of algorithms exist [Allen et al. 2002; Hähnel et al. 2003; Sumner and Popovi´c 2004].”
The space of human body shapes: reconstruction and parameterization from range scans (2003, methodology): “The parameterization method described in our previous work [Allen et al. 2002] might seem to be a candidate for solving this problem. There, we start from a subdivision template that resembles the range surface, then re-parameterize the surface by sampling it along the template normals to construct ”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, methodology): “correspondences [23], [29], [32], [34], [80].”
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation (2015, neutral): “• Mesh alignment is also standard pre-processing step in the analysis of three-dimensional meshes [1, 3, 9, 25].”