3D Hand Pose Estimation by Finding Appearance-Based Matches in a Large Database of Training Views
Vassilis Athitsos, Stan Sclaroff · 2001
Ongoing work towards appearance-based 3D hand pose estimation from a single image is presented. Using a 3D hand model and computer graphics a large database of synthetic views is generated. The views display different hand shapes as seen from arbitrary viewpoints. Each synthetic view is automatically labeled with parameters describing its hand shape and viewing parameters. Given an input image, the system retrieves the most similar database views, and uses the shape and viewing parameters of those views as candidate estimates for the parameters of the input image. Preliminary results are presented, in which appearance-based similarity is defined in terms of the chamfer distance between edge images. 1