Abstract

Projective analysis is an important solution for 3D shape retrieval, since human visual perceptions of 3D shapes rely on various 2D observations from different view points. Although multiple informative and discriminative views are utilized, most projection-based retrieval systems suffer from heavy computational cost, thus cannot satisfy the basic requirement of scalability for search engines. In this paper, we present a real-time 3D shape search engine based on the projective images of 3D shapes. The real-time property of our search engine results from the following aspects: (1) effificient projection and view feature extraction using GPU acceleration; (2) the fifirst inverted fifile, referred as F-IF, is utilized to speed up the procedure of multi-view matching; (3) the second inverted fifile (S-IF), which captures a local distribution of 3D shapes in the feature manifold, is adopted for effificient context-based reranking. As a result, for each query the retrieval task can be fifinished within one second despite the necessary cost of IO overhead. We name the proposed 3D shape search engine, which combines GPU acceleration and Inverted File (Twice), as GIFT. Besides its high effificiency, GIFT also outperforms the state-of-the-art methods signifificantly in retrieval accuracy on various shape benchmarks and competitions