Numerical Geometry of Non-Rigid Shapes

By A. Bronstein, Michael M. Bronstein, Ron Kimmel. 2009

841 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computational Mechanics, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

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

In Biomedical Engineering

1. Michael M. Bronstein
2. M. Ovsjanikov
3. Emanuele Rodolà
4. Michael J. Black
5. A. Bronstein
6. Davide Boscaini
7. Leonidas J. Guibas
8. Jonathan Masci

In Computational Mechanics

1. Michael M. Bronstein
2. Emanuele Rodolà
3. A. Bronstein
4. Michael J. Black
5. Davide Boscaini
6. Jonathan Masci
7. M. Ovsjanikov
8. Leonidas J. Guibas

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jitendra Malik
3. Dacheng Tao
4. Ming-Hsuan Yang
5. Andrea Vedaldi
6. Andrew Zisserman
7. Xiaogang Wang
8. Cordelia Schmid

In 3D Vision & Pose

1. Michael J. Black
2. Michael M. Bronstein
3. Gerard Pons-Moll
4. Jiajun Wu
5. Yaron Lipman
6. Mohammed Bennamoun
7. Josh Tenenbaum
8. Leonidas J. Guibas

Citations in the corpus

• Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “We also show correspondence on shapes from SCAPE [2] and TOSCA [9] datasets.”
• Generating 3D faces using Convolutional Mesh Autoencoders (2018, background): “Since changes in facial expression are near isometric deformations [9, Section 13.3], applying LBo to expressive faces would result in a loss of most expression-related shape variations, making it infeasible to model such variations.”
• Learning to Reconstruct Shapes from Unseen Classes (2018, methodology): “In Section 5, we also test our model on non-rigid shapes such as humans and horses [Bronstein et al., 2008] and on highly regular shape primitives.”
• Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (2018, background): “For decades, researchers have been building datasets of 3D objects, either as a repository of 3D CAD models [4, 5, 49] or as images of 3D shapes with pose annotations [34, 47].”
• FAUST: Dataset and Evaluation for 3D Mesh Registration (2014, methodology): “For a rough comparison, on 71 mesh pairs from SCAPE, [13] reports the same error threshold for 45% and 70% of the correspondences; on 80 mesh pairs from TOSCA, the same error is reported for 60% and 85% of the correspondences.”
• Self-supervised Learning of Dense Shape Correspondence (2018, neutral): “TOSCA dataset [13] includes various animal shapes.”
• Product Manifold Filter: Non-rigid Shape Correspondence via Kernel Density Estimation in the Product Space (2017, methodology): “Result of our method on two cat shapes from TOSCA [12].”
• Dense Non-rigid Shape Correspondence Using Random Forests (2014, methodology): “We perform these comparisons on the TOSCA high-resolution dataset [4].”
• Spatio-temporal Matching for Human Detection in Video (2014, background): “, non-rigid structure from motion, face animation), see [31].”
• Geodesic Convolutional Neural Networks on Riemannian Manifolds (2015, methodology): “In order to test the generalization capability of the learned descriptors, we applied OSD and GCNN learned on the FAUST dataset to TOSCA shapes (Figure 5, second row).”
• Functional maps (2012, methodology): “Both shape matching in general and non-rigid shape matching in particular are relatively well-established fields with several recent books (e.g. [Bronstein et al. 2008]) and surveys [van Kaick et al. 2011b] dedicated exclusively to this subject.”
• On Self-Contact and Human Pose (2021, background): “Even when the body is scanned in varied poses, these poses are designed to avoid self-contact [2, 6, 7, 37].”