Sparse localized deformation components

By T. Neumann, Kiran Varanasi, Stephan Wenger, M. Wacker, Marcus A. Magnor, Christian Theobalt. 2013

175 citations recorded by the source corpus.

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

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

1. Michael J. Black
2. Christian Theobalt
3. Timo Bolkart
4. Michael Zollhöfer
5. Gerard Pons-Moll
6. Ahmed A. A. Osman
7. Matthias Nießner
8. Jason M. Saragih

In Computer Graphics and Computer-Aided Design

1. Matthias Nießner
2. Christian Theobalt
3. Michael J. Black
4. Michael Zollhöfer
5. Justus Thies
6. Marc Stamminger
7. Andreas Geiger
8. Jason M. Saragih

In Control and Systems Engineering

1. Michael J. Black
2. Ahmed A. A. Osman
3. Christian Theobalt
4. Timo Bolkart
5. Yaser Sheikh
6. Pascal Fua
7. Naureen Mahmood
8. Dan Casas

Citations in the corpus

• Generating 3D faces using Convolutional Mesh Autoencoders (2018, neutral): “To capture localized facial details, Neumann et al. [33] and Ferrari et al. [19] use sparse linear models.”
• State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, background): “It is also possible to automatically compute sparse localized deformation components from sequences of face meshes [NVW ∗ 13], either fully-automatically or under user guidance, instead of using a pre-defined global or local region model.”
• MoSh (2014, methodology): “In [Neumann et al. 2013b] they develop methods for spatially localized modeling of deformations and show that these deformations can be edited and exaggerated.”
• Review of statistical shape spaces for 3D data with comparative analysis for human faces (2012, background): “Initial steps have been taken in this direction [75], although so far this is limited to sparsity through locality.”
• STAR: Sparse Trained Articulated Human Body Regressor (2020, methodology): “[27], use sparse PCA to learn local and sparse deformations of pose-dependent body deformations but do not learn a function mapping body pose to these deformations.”
• Modeling Facial Geometry Using Compositional VAEs (2018, background): “[26] extract sparse localized deformation components from an animated mesh sequence, for the purpose of intuitive editing as well as statistical processing of the face.”
• Reconstruction of Personalized 3D Face Rigs from Monocular Video (2016, background): “Approaches that extract components of face rigs from densely captured animation data, such as blendshape components [Neumann et al. 2013; Joshi et al. 2003], were also proposed, but despite its practical relevance, automatic rig creation received much less attention in research.”