#28950
"Smooth Shape Interpolation for 2D Polygons"
In 2D morphing, both source and target shapes can be triangulated into compatible polygons to establish correspondence. Once the correspondence between a source and a target 2D shape is established, the linear vertex interpolation is usually used for generating in-between shapes. However, this naïve scheme usually generates un-natural interpolated results. In this paper, we present a novel smooth shape interpolation scheme to generate visual pleasing morphs between 2D polygons. Each triangle in a compatible triangulation is represented by a stick structure. The intermediate shape of a triangle is interpolated using this stick structure. All of these intermediate triangles are then assembled together according to a predetermined order. Several examples of aesthetically pleasing morphs are demonstrated using the proposed method. All of these morph sequences can be generated in real time.
#28877
"Dual Laplacian Morphing for Triangular Meshes"
Recently, animations with deforming objects have been frequently used in various computer graphics applications. Morphing of objects is one of the techniques which realize shape transformation between two or more existing objects. In this paper, we present a novel morphing approach for 3D triangular meshes which share the same topology. The basic idea of our method is to interpolate the mean curvature flow of the input meshes as the curvature flow Laplacian operator encodes the intrinsic local information of the mesh. The in-between meshes are recovered from the interpolated mean curvature flow in the dual mesh domain due to the simplicity of the neighborhood structure of dual mesh vertices. Our approach can generate visual pleasing and physical plausible morphing sequences that can avoid the shrinkage and kinks appeared in the linear interpolation method. Many experimental results are presented to show the applicability and flexibility of our approach.
#29440
"Human Hand Adaptation Using Sweeps: Generating Animatable Hand Models"
We introduce a sweep-based hand shape adaptation algorithm to fit a generic sweep-based hand model to the shape of an individual's hand, presented as a single photograph. The sweep trajectory curves of the generic hand model are modified to interpolate a sequence of keyframes determined by target features. Details of the real hand can be transferred to the model by adjusting its sweep displacement map. Palm lines are also acquired from sketches drawn on the photograph. The bespoke model inherits the fully animatable structure of the generic model. We demonstrate the effectiveness of our sweepbased approach using several examples of reconstructing animatable bespoke hand models.
#29445
"Stylized Synthesis of Facial Speech Motions"
Stylized synthesis of facial speech motions is central to facial animation. Most synthesis algorithms put emphasis on the reasonable concatenation of captured motion segments. The dynamical modeling of speech units, e.g. visemes and visyllables, has drawn little attentions. In this paper, we address the fundamental issues regarding the stylized dynamical modeling of visyllables. The decomposable generalized model is learnt for the stylized motion synthesis. The visyllable modeling includes two parts: (1) A dynamical model for each kinds of visyllable that are learnt based on Gaussian Process Dynamical Model; (2) A multilinear model based unified mapping between the high dimensional observation space and low dimensional latent space. The dynamical visyllable model embeds the high dimensional motion data to a low dimensional latent space, and constructs the dynamical mapping in the latent space simultaneously. To generalize the visyllable model from several instances, the mapping coefficient matrices are assembled to a tensor, which is decomposed into independent modes, e.g. identity, uttering styles. Therefore, with free combination of components in each mode, the novel stylized motion can be synthesized.
#29443
"Perceptive Animated Agent Based Virtual Speech Therapy System"
The prevalence of disordered communication is particularly high in individuals diagnosed with idiopathic Parkinson disease (IPD). At least 89% of these individuals have disordered speech and voice but only 3-4% received speech treatment. LSVT (Lee Silverman Voice Treatment) is a speech and voice treatment for individuals with Parkinson disease. It is the only speech treatment with Level one short and long-term efficacy data for Parkinson disease. LSVT teaches people to think and talk Loud. In this paper, we developed a LSVT virtual speech therapy system based on a perceptive animated agent. The main goals of this system is to develop a fully automated computer application in which a perceptive animated agent interacts with an individual with IPD much like a human therapist to increase the loudness and improve the quality and intelligibility of the patients speech, thus provide an accessible, engaging, inexpensive and highly effective means of improving communication skills, self esteem and quality of everyday life of individuals with IPD.
#29001
"Approximating Character Biomechanics with Real Time Weighted Inverse Kinematics"
In this paper we show how the expensive, offline dynamic simulations of character motions can be approximated using the cheaper weighted inverse kinematics-based approach. We first show how a dynamics-based approach can be used to produce a motion that is representative of a real target actor using the motion of a different source actor and the biomechanics of the target actor. This is compared against a process that uses weighted inverse kinematics to achieve the same motion mapping goal without direct biomechanical input. The parallels between the results of the two approaches are described and further reasoned from a mathematical perspective. Thus we demonstrate how character biomechanics can be approximated with real-time weighted inverse kinematics.