Embedded deformation for shape manipulation

By Robert W. Sumner, Johannes Schmid, Mark Pauly. ACM Transactions on Graphics, 2007

690 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/8f6d018b669a95bc5762699b322b19145c24821b

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 Graphics and Computer-Aided Design

In Control and Systems Engineering

Citations in the corpus

Elastic Fragments for Dense Scene Reconstruction (2013, background): “where N (p) is the set of neighbors of p in Gi, and Rp is a rotation transform that maps the local tangent frame of p to the local tangent frame of p′ [28, 30].”
Robust single-view geometry and motion reconstruction (2009, methodology): “We extend the embedded deformation framework proposed in [Sumner et al. 2007] to automatically adapt to the motion of the captured data.”
Shape Completion from a Single RGBD Image (2017, methodology): “After the rigid alignment, the embedded deformation model [33] is applied to perform nonrigid alignment.”
Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems (2021, methodology): “points" in [88] will be the keyframes in our trajectory.”
Blending liquids (2014, methodology): “We perform this deformation using a variation of the embedded deformation model first introduced by Sumner and colleagues in [Sumner et al. 2007] and extended by Li and colleagues in [Li et al.”
User-Specific Hand Modeling from Monocular Depth Sequences (2014, background): “Several related deformations have been defined, including Laplacian-based measures [23] and ‘embedded deformation’ [26], and our choice of ARAP is to some extent arbitrary, but exploration of the alternatives is left to future work.”
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (2023, positive): “We derive the dense motion field of Gaussians using linear blend skin-ning (LBS) [44] by locally interpolating the transformations of their neighboring control points.”
Nerfies: Deformable Neural Radiance Fields (2020, methodology): “It is common in geometry processing and physics simulation to model non-rigid deformations using elastic energies measuring the deviation of local deformations from a rigid motion [8, 13, 51, 52].”
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor (2018, background): “[35] to parameterize the pre-scanned template to produce locally as-rigid-as-possible deformation.”
Scanning 3D Full Human Bodies Using Kinects (2012, methodology): “The energy is minimized using standard Gauss-Newton algorithm as described in [17].”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, methodology): “2013) accomplishes this in two optimization step: first it optimizes the pose graph and, by utilizing the relationship between the vertices of the mesh and the poses in the pose graph, it then uses the optimized pose graph as measurement constraints in order to deform the mesh with a deformation gra”
Holoportation: Virtual 3D Teleportation in Real-time (2016, methodology): “Following [14], we parameterize the nonrigid deformation using the embedded deformation (ED) model of [54].”
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time (2015, background): “Hierarchical Deformation Tree: In original applications of the embedded deformation graph [25] approach to non-rigid tracking, E is defined as the k−nearest neighbours of each node or all nodes within a specified radius.”
ElasticFusion: Dense SLAM Without A Pose Graph (2015, methodology): “This method is computationally efficient (compared to spatial approaches [23, 1]) but more importantly prevents temporally uncorrelated areas of the surface from influencing each other (i.”