Facial animation retargeting framework using radial basis functions
نویسندگان
چکیده
In this paper we demonstrate our framework of facial motion retargeting. We define pairs of source and target expressions and their variable configurations. For a given new source expression the target variables are automatically adjusted accordingly. We use Radial Basis Function (RBF) based regression methods to define the relationship between source and target configurations. We also investigate both realtime use with markerless capture data from web cameras, and high quality methods for production environments based on professional motion capture systems. We show that the method can handle a wide range of animation parameter types including skinning, blend shapes and material properties.
منابع مشابه
High-resolution Animation of Facial Dynamics
This paper presents a framework for performance-based animation and retargeting of high-resolution face models from motion capture. A novel method is introduced for learning a mapping between sparse 3D motion capture markers and dense high-resolution 3D scans of face shape and appearance. A high-resolution facial expression space is learnt from a set of 3D face scans as a person specific morpha...
متن کاملA New Compatible Remeshing Approach for 3D Face Construction and Expression Clone
This paper presents a new compatible remeshing approach, by morphing with Radial Basis Function based on approximate geodesic distance (G-RBF) followed by a mesh optimization to generate compatible meshes efficiently while approximating the input target geometry accurately. To test the proposed approach, a prototype is implemented to clone expressions onto the personalized 3D face model. A PCA ...
متن کاملFacial Motion Cloning Using Global Shape Deformation
We present a novel Facial Motion Cloning method relying on the combination of the radial basis functions (RBF) based scattered data interpolation with the encoding capabilities of the MPEG-4 Facial and Body Animation (FBA) international standard. Beside from an initial manual selection of feature points, our method works fully automatically without user interaction. The produced talking head is...
متن کاملDelaunay Triangles Model for Image-Based Motion Retargeting
We present an automatic system for retargeting a human body motion extracted from an image sequence into a new character in a still image. In contrast to analyzing the articulated motion of its skeleton in the previous vision-based human body tracking and posture recognition system, we use direct 2-D image warping based on a silhouette. At first, we represent the performer’s silhouette with the...
متن کاملKernel Projection of Latent Structures Regression for Facial Animation Retargeting
Inspired by kernel methods that have been used extensively in achieving efficient facial animation retargeting, this paper presents a solution to retargeting facial animation in virtual character’s face model based on the kernel projection of latent structure (KPLS) regression between semantically similar facial expressions. Specifically, a given number of corresponding semantically similar fac...
متن کامل