Histograms of Oriented Gradients for 3D Object Retrieval

Abstract

3D object retrieval has received much research attention during the last years. To automatically determine the
\nsimilarity between 3D objects, the global descriptor approach is very popular, and many competing methods for
\nextracting global descriptors have been proposed to date. However, no single descriptor has yet shown to outperform
\nall other descriptors on all retrieval benchmarks or benchmark classes. Instead, combinations of different
\ndescriptors usually yield improved performance over any single method. Therefore, enhancing the set of candidate
\ndescriptors is an important prerequisite for implementing effective 3D object retrieval systems.
\nInspired by promising recent results from image processing, in this paper we adapt the Histogram of Oriented Gradients
\n(HOG) 2D image descriptor to the 3D domain. We introduce a concept for transferring the HOG descriptor
\nextraction algorithm from 2D to 3D. We provide an implementation framework for extracting 3D HOG features
\nfrom 3D mesh models, and present a systematic experimental evaluation of the retrieval effectiveness of this novel
\n3D descriptor. The results show that our 3D HOG implementation provides competitive retrieval performance,
\nand is able to boost the performance of one of the best existing 3D object descriptors when used in a combined
\ndescriptor.