Abstract: This paper proposes a novel 3D shape retrieval method for articulated shape models. The proposed method is composed of a topological matching step based on skeleton graph and a geometric matching step based on shape diameter function. In the first step, the curve skeletons of the shape models are extracted and a similarity measure based on skeleton graph is used for 3D shape retrieval. In the second step, a "slim-fat" shape descriptor is calculated and the shape retrieval process can further sort shape models with this shape descriptor. Experimental results show that our method produces an efficient and accurate result.
Publication Year: 2016
Publication Date: 2016-08-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot