A Statistical Model of Human Pose and Body Shape

By Nils Hasler, Carsten Stoll, Martin Sunkel, Bodo Rosenhahn, Hans-Peter Seidel. Computer graphics forum (Print), 2009

473 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/650b04ffc4e5911137c86263e11ea3cdb474e501

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 Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Capturing the human figure through a wall (2015, methodology): “We envision that exploiting more powerful segmentation and pose estimation algorithms – such as those that employ recognition or probabilistic labeling, e.g., [Mori et al. 2004; Shotton et al. 2013; Hasler et al. 2009a] – would capture better human ﬁgures.”
Sparse localized deformation components (2013, methodology): “We exemplify it on the problem of building a static statistical shape model of human shape variations from a large corpus of laser scans of real human subjects, which are previously done with PCA and bilinear models [Anguelov et al. 2005; Hasler et al. 2009].”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, methodology): “Top-down, model-based methods exploit a parametric body model consisting of pose and shape [7, 33, 48, 89, 57, 40] to regularize the fitting process.”
Morphable Face Models - An Open Framework (2017, methodology): “The iterative closest point algorithm (ICP) [5] and its nonrigid extension (NICP), introduced by [2] and [6] are the most popular algorithms used for establishing the correspondence of 3D face shapes ([4],[7],[8],[9],[10]).”
Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “More recent models are estimated from multiple scans of diverse people (Hasler et al., 2009; Loper et al., 2015; Pons-Moll et al., 2015; Zu ﬃ and Black, 2015) or combination of different body models (Joo et al., 2018).”
Learning a model of facial shape and expression from 4D scans (2017, methodology): “Consequently one could learn a mapping from our space to semantic attributes as shown in other works [Allen et al. 2003; Hasler et al. 2009; Vlasic et al. 2005] or train a localized space as proposed by Neumann et al. [2013] from our provided expression registration, and replace the global…”
Resolving 3D Human Pose Ambiguities With 3D Scene Constraints (2019, background): “It goes beyond similar models [6, 26, 40, 57] by holistically modeling the body with facial expressions and finger articulation, which is important for interactions.”
User-Specific Hand Modeling from Monocular Depth Sequences (2014, background): “Examples include morphable models and their successors [5, 2, 3, 8], which we shall call parameterized class models (PCMs).”
Dynamic FAUST: Registering Human Bodies in Motion (2017, background): “In 3D registration, the FAUST dataset [8] filled a gap since other datasets were either synthetic [13, 14, 32] or without ground truth [4, 28, 42].”
Detailed, Accurate, Human Shape Estimation from Clothed 3D Scan Sequences (2017, methodology): “Some works model shape and pose deformations jointly as in [16] where they perform PCA on a rotation-invariant encoding of triangles.”
Multilinear pose and body shape estimation of dressed subjects from image sets (2010, background): “[9] in various contexts, it is easy to enforce several such constraints for any PCA based approach [12].”
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (2019, methodology): “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].”
On Self-Contact and Human Pose (2021, methodology): “To simplify the process for workers on AMT, we give detailed instructions, add thumbnails to compare the own image with the presented one and, most importantly, highlight the contact areas; see Fig.”
Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, methodology): “The parameterized models are then encoded by the rotation invariant model representation approach in [34] where the differences between a pair of scans can easily be extracted in training.”
Multi-Garment Net: Learning to Dress 3D People From Images (2019, background): “current statistical models can not represent clothing, most works [7, 26, 40, 68, 48, 32, 22, 67, 31, 50, 8, 33, 44, 46] are restricted to inferring body shape alone.”
Embodied hands (2017, background): “SCAPE achieved high realism and spawned many related approaches [Chen et al. 2013; Freifeld and Black 2012; Hasler et al. 2009; Hirshberg et al. 2012; Pons-Moll et al. 2015].”
FAUST: Dataset and Evaluation for 3D Mesh Registration (2014, background): “Human body shape modeling has received a great deal of attention recently [10, 11, 12] but there is a paucity of high-quality scan data for building and evaluating such models.”