Global Correspondence Optimization for Non‐Rigid Registration of Depth Scans

By Hao Li, Robert W. Sumner, Mark Pauly. Computer graphics forum (Print), 2008

511 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f37865c0769e5a83c925a29321b6e7615d44da4c

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, background): “Handling Holes: [31] avoids the effects of holes due to”
DART: Dense Articulated Real-Time Tracking (2014, background): “However, the full generality of these models comes at the cost of increased model complexity, and for many objects that are well modelled as piecewise rigid bodies, such overparameterized output obscures the utility of tracking the articulated body state directly.”
Learning an efficient model of hand shape variation from depth images (2015, background): “Learning a lower dimensional parametrization of shape from examples of range scans or other 3D data has proved effective in creating generic morphable models for human bodies and faces [7, 4, 5, 13, 10, 29, 17, 27, 30, 16, 31, 19].”
Blended intrinsic maps (2011, methodology): “This method is most commonly used for aligning surfaces related by a rigid transformation [Besl and McKay 1992], but has also been used for moderate non-rigid deformations [Allen et al. 2003; Brown and Rusinkiewicz 2007; Li et al. 2008; Pauly et al. 2005; Tevs et al. 2009; Ghosh et al. 2009].”
Möbius voting for surface correspondence (2009, background): “, for registration of poorly calibrated range scans [Brown and Rusinkiewicz 2007; Li et al. 2008], for statistical analysis of similar objects in the same pose [Allen et al.”
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor (2018, methodology): “In the last decades, many methods have been proposed to address free-form capture: linear variational deformation [20], deformation graph [18], subspace deformation [40], articulate deformation [7, 8] and [29], 4D spatio-temporal surface [26] and [36], incompressible flows [33], animation cartograph”
One Point Isometric Matching with the Heat Kernel (2010, unknown): “Several variants of the classical ICP algorithm have been proposed to match deformable shapes when the deformation between them is small (e.g. [ACP03,WJH + 07,LSP08]).”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “A smooth locally affine model is introduced as the transformation model and developed under the ICP framework in non-rigid ICP (Amberg et al. 2007), which is also adopted in Li et al. (2008).”
Dynamic shape capture using multi-view photometric stereo (2009, methodology): “Second, our data is ideally suited as input to algorithms that perform temporal registration and merging of geometry, which have recently received considerable interest in the geometry processing community [Wand et al. 2007; Huang et al. 2008; Li et al. 2008; Sharf et al. 2008; Zhang et al. 2008; Wa”
Dense Human Body Correspondences Using Convolutional Networks (2015, methodology): “osed by Chen et al. [11], which uses the initial poses of the models to reﬁne correspondences. To make a fair comparison with Chen et al. [11], we run an outof-the-shelf non-rigid registration method [24] to improve the correspondences. Both result are reported in Figure. 8 and Table. 3. It is worth”
Robust single-view geometry and motion reconstruction (2009, methodology): “To avoid local minima in the non-linear optimization, we use the simple yet effective technique proposed by [Li et al. 2008] that progressively relaxes the regularization energies of the deformation model.”