Sphere Image for 3-D Model Retrieval
Ke Ding, Yunhui Liu · IEEE Transactions on Multimedia · 2014
The view-based 3-D model retrieval system represents a 3-D model by its projected views. Most of the existing view-based 3-D model retrieval systems only analyze the features of the projected views, but not well consider the spatial arrangements of the viewpoints. Furthermore, most of these systems suffer from the high computational cost due to pairwise comparing the projected views of 3-D models. In this paper, we propose a new 3-D model descriptor called Sphere Image, which is defined as a collection of view features. A viewpoint of a 3-D model is regarded as a “pixel”: (1) The position of the viewpoint is denoted as the coordinate of the “pixel”. (2) The feature descriptor of the projected view is denoted as the value of the “pixel”. We also propose a probabilistic graphical model for 3-D model matching, and develop a 3-D model retrieval system to test our approach. We have conducted experiments based on the SHape REtrieval Contest (SHREC) 2012 generic 3-D model date set and the SHREC2009 partial 3-D model data set. Experimental results indicate that our system outperforms some state-of-the-art 3-D model retrieval systems.