Robust wrinkle-aware non-rigid registration for triangle meshes of hand with rich and dynamic details

Consistence of topology for 3D models with such rich details as pores and wrinkles is very important for performing higher level tasks like deformation and animation. In this paper, we propose a novel wrinkle-aware registration method, which aligns not only the large-scale poses, but also high-resolution deformable details, in a unified framework. Using large-scale alignment enables us to solve a template-based energy minimization problem through pure Euclidean measurement. Fine-scale features are aligned by firstly computing crest lines for both the intermediately registered mesh and the target, and then evaluating the shape descriptors at the feature points, followed by a graph matching procedure to achieve a global optimization of the closest point matching. Experiments show that our method is effective and robust in preserving the quality of the source, while matching the fine-scale details of the target.

Figure optionsDownload high-quality image (183 K)Download as PowerPoint slideHighlights
► We align not only the large-scale poses of hands, but also high-resolution deformable details, in a unified framework.
► We use crest lines detection algorithm for feature extraction.
► Graph matching on crest lines will obtain a global optimization on correspondence.
► We examine changes by different markers, model completion, impact of flex and stretched poses, and different resolutions of models.