Results 1 -
7 of
7
Review of statistical shape spaces for 3D data with comparative analysis for human faces
- Computer Vision and ImageUnderstanding
, 2014
"... With systems for acquiring 3D surface data being evermore commonplace, it has become important to reliably extract spe-cific shapes from the acquired data. In the presence of noise and occlusions, this can be done through the use of statisti-cal shape models, which are learned from databases of clea ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
With systems for acquiring 3D surface data being evermore commonplace, it has become important to reliably extract spe-cific shapes from the acquired data. In the presence of noise and occlusions, this can be done through the use of statisti-cal shape models, which are learned from databases of clean examples of the shape in question. In this paper, we review, analyze and compare different statistical models: from those that analyze the variation in geometry globally to those that analyze the variation in geometry locally. We first review how different types of models have been used in the literature, then proceed to define the models and analyze them theoretically, in terms of both their statistical and computational aspects. We then perform extensive experimental comparison on the task of model fitting, and give intuition about which type of model is better for a few applications. Due to the wide avail-ability of databases of high-quality data, we use the human face as the specific shape we wish to extract from corrupted data. 1
Subspace Clothing Simulation Using Adaptive Bases
"... Figure 1: Example result of our method: A close-fitting sweater exhibits wrinkles and torsional folds under the effects of gravity and as the underlying torso is twisting. This example used only 12 adaptively chosen basis vectors and ran 18 times faster than a full simulation. We present a new appro ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
Figure 1: Example result of our method: A close-fitting sweater exhibits wrinkles and torsional folds under the effects of gravity and as the underlying torso is twisting. This example used only 12 adaptively chosen basis vectors and ran 18 times faster than a full simulation. We present a new approach to clothing simulation using low-dimensional linear subspaces with temporally adaptive bases. Our method exploits full-space simulation training data in order to construct a pool of low-dimensional bases distributed across pose space. For this purpose, we interpret the simulation data as offsets from a kinematic deformation model that captures the global shape of clothing due to body pose. During subspace simulation, we se-lect low-dimensional sets of basis vectors according to the current pose of the character and the state of its clothing. Thanks to this adaptive basis selection scheme, our method is able to reproduce diverse and detailed folding patterns with only a few basis vectors. Our experiments demonstrate the feasibility of subspace clothing simulation and indicate its potential in terms of quality and compu-tational efficiency.
Semantic Parametric Reshaping of Human Body Models
- In Proceedings of the 2014 2nd International Conference on 3D Vision
, 2014
"... Abstract-We develop a novel approach to generate human body models in a variety of shapes and poses via tuning semantic parameters. Our approach is investigated with datasets of up to 3000 scanned body models which have been placed in point to point correspondence. Correspondence is established by ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract-We develop a novel approach to generate human body models in a variety of shapes and poses via tuning semantic parameters. Our approach is investigated with datasets of up to 3000 scanned body models which have been placed in point to point correspondence. Correspondence is established by nonrigid deformation of a template mesh. The large dataset allows a local model to be learned robustly, in which individual parts of the human body can be accurately reshaped according to semantic parameters. We evaluate performance on two datasets and find that our model outperforms existing methods.
3D Faces in Motion: Fully Automatic Registration and Statistical Analysis
"... This paper presents a representation of 3D facial motion sequences that allows performing statistical analysis of 3D face shapes in motion. The resulting statistical analysis is applied to automatically generate realistic facial animations and to recognize dynamic facial expressions. To perform stat ..."
Abstract
- Add to MetaCart
This paper presents a representation of 3D facial motion sequences that allows performing statistical analysis of 3D face shapes in motion. The resulting statistical analysis is applied to automatically generate realistic facial animations and to recognize dynamic facial expressions. To perform statistical analysis of 3D facial shapes in motion over different subjects and different motion sequences, a large database of motion sequences needs to be brought in full correspondence. Existing algorithms that compute correspondences between 3D facial motion sequences either require manual input or suffer from instabilities caused by drift. For large databases, algorithms that require manual interaction are not practical. We propose an approach to robustly compute correspondences between a large set of facial motion sequences in a fully automatic way using a multilinear model as statistical prior. In order to register the motion sequences, a good initialization is needed. We obtain this initialization by introducing a landmark prediction method for 3D motion sequences based on Markov Random Fields. Using this motion sequence registration, we find a compact representation of each motion sequence consisting of one vector of coefficients for identity and a high dimensional curve for expression. Based on this representation, we synthesize new motion sequences and perform expression recognition. We show experimentally that the obtained registration is of high quality, where 56 % of all vertices are at distance at most 1mm from the input data, and that our synthesized motion sequences look realistic.
Linear Subspace Design for Real-Time Shape Deformation
"... Figure 1: Our linear subspaces are very fast to compute. This enables the users to add (or remove) control handles very quickly, allowing them to realize their creative intent in a single interactive session. We propose a method to design linear deformation subspaces, uni-fying linear blend skinning ..."
Abstract
- Add to MetaCart
Figure 1: Our linear subspaces are very fast to compute. This enables the users to add (or remove) control handles very quickly, allowing them to realize their creative intent in a single interactive session. We propose a method to design linear deformation subspaces, uni-fying linear blend skinning and generalized barycentric coordi-nates. Deformation subspaces cut down the time complexity of variational shape deformation methods and physics-based anima-tion (reduced-order physics). Our subspaces feature many desirable properties: interpolation, smoothness, shape-awareness, locality, and both constant and linear precision. We achieve these by min-imizing a quadratic deformation energy, built via a discrete Lapla-cian inducing linear precision on the domain boundary. Our main advantage is speed: subspace bases are solutions to a sparse lin-ear system, computed interactively even for generously tessellated domains. Users may seamlessly switch between applying transfor-mations at handles and editing the subspace by adding, removing or relocating control handles. The combination of fast computation and good properties means that designing the right subspace is now just as creative as manipulating handles. This paradigm shift in handle-based deformation opens new opportunities to explore the space of shape deformations.
Computational Bodybuilding: Anatomically-based Modeling of Human Bodies
"... Figure 1: Given an input 3D anatomy template, we propose a system to simulate the effects of muscle, fat, and bone growth. This allows us to create a wide range of human body shapes. We propose a method to create a wide range of human body shapes from a single input 3D anatomy template. Our approach ..."
Abstract
- Add to MetaCart
Figure 1: Given an input 3D anatomy template, we propose a system to simulate the effects of muscle, fat, and bone growth. This allows us to create a wide range of human body shapes. We propose a method to create a wide range of human body shapes from a single input 3D anatomy template. Our approach is inspired by biological processes responsible for human body growth. In par-ticular, we simulate growth of skeletal muscles and subcutaneous fat using physics-based models which combine growth and elas-ticity. Together with a tool to edit proportions of the bones, our method allows us to achieve a desired shape of the human body by directly controlling hypertrophy (or atrophy) of every muscle and enlargement of fat tissues. We achieve near-interactive run times by utilizing a special quasi-statics solver (Projective Dynamics) and by crafting a volumetric discretization which results in accurate defor-mations without an excessive number of degrees of freedom. Our system is intuitive to use and the resulting human body models are ready for simulation using existing physics-based animation meth-ods, because we deform not only the surface, but also the entire volumetric model.
EUROGRAPHICS 2014 / S. Lefebvre and M. Spagnuolo STAR – State of The Art Report Practice and Theory of Blendshape Facial Models
"... “Blendshapes”, a simple linear model of facial expression, is the prevalent approach to realistic facial animation. It has driven animated characters in Hollywood films, and is a standard feature of commercial animation packages. The blendshape approach originated in industry, and became a subject o ..."
Abstract
- Add to MetaCart
“Blendshapes”, a simple linear model of facial expression, is the prevalent approach to realistic facial animation. It has driven animated characters in Hollywood films, and is a standard feature of commercial animation packages. The blendshape approach originated in industry, and became a subject of academic research relatively recently. This course describes the published state of the art in this area, covering both literature from the graphics research community, and developments published in industry forums. We show that, despite the simplicity of the blendshape approach, there remain open problems associated with this fundamental technique.
