We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity-dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. We quantitatively evaluate variants of SMPL using linear or dual-quaternion blend skinning and show that both are more accurate than a Blend-SCAPE model trained on the same data. We also extend SMPL to realistically model dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.

SMPL: a skinned multi-person linear model

A major unsolved problem in computer graphics is the construction and animation of realistic human facial models. Traditionally, facial models have been built painstakingly by manual digitization and animated by ad hoc parametrically controlled facial mesh deformations or kinematic approximation of muscle actions. Fortunately, animators are now able to digitize facial geometries through the use of scanning range sensors and animate them through the dynamic simulation of facial tissues and muscles. However, these techniques require considerable user input to construct facial models of individuals suitable for animation. In this paper, we present a methodology for automating this challenging task. Starting with a structured facial mesh, we develop algorithms that automatically construct functional models of the heads of human subjects from laser-scanned range and reflectance data. These algorithms automatically insert contractile muscles at anatomically correct positions within a dynamic skin model and root them in an estimated skull structure with a hinged jaw. They also synthesize functional eyes, eyelids, teeth, and a neck and fit them to the final model. The constructed face may be animated via muscle actuations. In this way, we create the most authentic and functional facial models of individuals available to date and demonstrate their use in facial animation.

/pdf/realistic-modeling-for-facial-animation-g24yr1j03a.pdf

Realistic modeling for facial animation

We present new techniques for creating photorealistic textured 3D facial models from photographs of a human subject, and for creating smooth transitions between different facial expressions by morphing between these different models. Starting from several uncalibrated views of a human subject, we employ a user-assisted technique to recover the camera poses corresponding to the views as well as the 3D coordinates of a sparse set of chosen locations on the subject's face. A scattered data interpolation technique is then used to deform a generic face mesh to fit the particular geometry of the subject's face. Having recovered the camera poses and the facial geometry, we extract from the input images one or more texture maps for the model. This process is repeated for several facial expressions of a particular subject. To generate transitions between these facial expressions we use 3D shape morphing between the corresponding face models, while at the same time blending the corresponding textures. Using our technique, we have been able to generate highly realistic face models and natural looking animations.

/pdf/synthesizing-realistic-facial-expressions-from-photographs-2djj726bej.pdf

Synthesizing realistic facial expressions from photographs

We describe a multiresolution representation for meshes based on subdivision, which is a natural extension of the existing patch-based surface representations. Combining subdivision and the smoothing algorithms of Taubin [26] allows us to construct a set of algorithms for interactive multiresolution editing of complex hierarchical meshes of arbitrary topology. The simplicity of the underlying algorithms for refinement and coarsification enables us to make them local and adaptive, thereby considerably improving their efficiency. We have built a scalable interactive multiresolution editing system based on such algorithms.

/pdf/interactive-multiresolution-mesh-editing-31sxy1apjv.pdf

Interactive multiresolution mesh editing

Head-worn adaptive display

A simple differential equation method is proposed for modeling the aesthetic features of human hair. In the method, a simplified cantilever beam simulation is employed for hairstyle modeling, which allows hairdressing variations with volumetric and realistic appearance. In order to describe the dynamical behavior of hair in an animation, one-dimensional projective differential equations of angular momenta for linked rigid sticks are also derived. For the problem of collision detection between hair and a human head, the “rough” approximate solution is provided, which gives visually satisfactory results by solving the projective equations under a ps~udo-force field. The hair’s pliability can be controlled by using a set of stiffness parameters in the method. In addition, a fast rendering technique for anisotropic reflection is introduced, which is derived from Blirm’s specular model. The efficiency of the proposed method is illustrated by the still images and short animations obtained. CR

A simple method for extracting the natural beauty of hair

This paper presents a new method for constructing an example-based deformable human hand model from medical images. Realistic animation of human hands requires good estimates of the joint structure and properly weighted skeleton-driven surface deformation. For this purpose, we propose a method based on medical images of hands in several poses. Our method consists of the following 3 steps: First, using the measured bone shapes, we estimate the link structure (joint rotation centers) and the joint angles of each scan. Second, we construct a mutually consistent polygonal mesh of all the scans. For this purpose, a polygonal mesh of one pose, the base mesh, is deformed using skeletal subspace deformation, and then fitted interactively to the measured meshes from the other scans. Finally, the hand is deformed using a weighted pose space deformation. We demonstrate results of deformable hand models consisting of 100,000 triangle meshes derived from CT scans.

Modeling deformable human hands from medical images

This invention relates to a graphic data processing system, and is more particularly directed to provide an easy-to-operate system and displaying method thereof, for generating scene data from map data and retrieving and displaying attributes containing guide information of ground objects in a scene. In the first place, when a visual point is directed from above to below, a planar map is displayed, and as the visual point shifts in a horizontal direction, a three-dimensional scene image is generated and displayed from a map. Secondly, a three-dimensional window is displayed in a display, and graphic data is displayed inside the window.

Graphic data processing system

There are basically four problems to solve in order to produce realistic animated synthetic actors with hair: hair modeling and creation, hair motion, collision detection and hair rendering. The authors describe a complete methodology to solve these basic four problems. They present how hair styles may be designed with a Hair Styler module. They survey the animation model and emphasize a method of collision processing. Finally, they explain how hair may be rendered using an extension of a standard ray-tracing program. Applications of synthetic actors with various hair styles and different styles of mustaches and beards are shown

An integrated system for modeling, animating and rendering hair

This paper describes a new transformation method for modeling and animation of the human face. A 3-D canonical facial model is introduced which is transformed to a facial model that is consistent with photographs of an individual face. Facial expression is modified by transformation of the obtained facial model. By using the displacements of selected control points, the transformation determines the displacements of the remaining points by linear interpolation in a 2-D parameter space. To generate texturemapped facial images, photographs are first projected onto a 2-D space using cylindrical coordinates and then combined, taking into account their positional certainty.

Tsuneya Kurihara

Papers

A simple method for extracting the natural beauty of hair

Modeling deformable human hands from medical images

Graphic data processing system

An integrated system for modeling, animating and rendering hair

A Transformation Method for Modeling and Animation of the Human Face from Photographs