The space of human body shapes: reconstruction and parameterization from range scans

By Brett Allen, Brian Curless, Zoran Popovic. ACM Transactions on Graphics, 2003

1,282 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6386560c664204ee909b252008d1e69263a68268

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. Leonidas J. Guibas
3. Gerard Pons-Moll
4. Michael M. Bronstein
5. Thomas A. Funkhouser
6. Yaron Lipman
7. Vladimir G. Kim
8. Niloy J. Mitra

In Computer Vision and Pattern Recognition

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

Citations in the corpus

• Blended intrinsic maps (2011, methodology): “With such a map, it is possible to transfer attributes [Kraevoy and Sheffer 2004], study surface variations [Allen et al. 2003], and process meshes consistently [Golovinskiy and Funkhouser 2009].”
• SCAPE: shape completion and animation of people (2005, methodology): “We also added eight publicly available models from the CAESAR data set [Allen et al. 2003] to our data set of individuals.”
• Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (2019, background): “Models of the 3D body have focused on capturing the overall shape and pose of the body, excluding the hands and face [2, 3, 6, 26, 48].”
• Review of statistical shape spaces for 3D data with comparative analysis for human faces (2012, neutral): “Allen et al. [22] proposed a statistical model for human body shapes acquired in a similar posture that is similar to the mor-phable face model introduced by Blanz and Vetter.”
• Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, methodology): “In [33] a statistical shape model is learned by principal component analysis (PCA) and used to synthesize individual subjects using a template-based method.”
• Capturing the human figure through a wall (2015, methodology): “The first category is high-frequency imaging radar using terahertz [Woodward et al. 2002], laser [Allen et al. 2003], or millimeter and sub-millimeter waves [Cooper et al. 2008; Dengler et al. 2007; Appleby and An-derton 2007].”
• Home 3D body scans from noisy image and range data (2011, background): “[3] in spirit, but is the inverse of the problem they describe.”
• Optimal Step Nonrigid ICP Algorithms for Surface Registration (2007, methodology): “A version based on the locally affine regularisation from [1], and an algorithm using locally smooth translations is developed.”
• Multi-chart generative surface modeling (2018, background): “Another line of works tried to learn the shape space of a certain class of shapes; [3, 4, 24] have all targeted the shape of the human body.”
• Robust single-view geometry and motion reconstruction (2009, methodology): “Various methods make use of a template model to simplify correspondence estimation and provide a prior for geometry and topology reconstruction, often relying on a small set of manually specified correspondences [Blanz and Vetter 1999; Allen et al. 2003; Pauly et al. 2005; Amberg et al. 2007].”
• OpenDR: An Approximate Differentiable Renderer (2014, methodology): “This dataset comes with anthropometric measurements for each subject; similar to [1], we use regularized linear regression to predict measurements from our underlying body shape parameters.”
• Geometric modeling in shape space (2007, methodology): “Other approaches for more specific tasks e.g. for parametrization and animation of human body poses [Allen et al. 2003; Anguelov et al. 2005] as well as example based methods [Sloan et al. 2001] can be found in the literature.”
• 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].”
• What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, methodology): “[234] that developed a method for fitting high-resolution template meshes to 250 detailed human body range scans from the 3D CAESAR database9 with sparse 3D markers to model the variation of different bodies.”