Shape google

TLDR

Recent advances in computer vision have popularized feature‑based methods that represent images as collections of visual words and apply bag‑of‑features text search techniques. This study investigates applying bag‑of‑features techniques to nonrigid 3D shape retrieval in large databases. The authors build shape descriptors from multiscale diffusion heat kernels as geometric words, then use metric learning to encode shapes as compact binary codes. The resulting method, which uses geometric expressions and binary coding, achieves state‑of‑the‑art performance on the SHREC 2010 shape retrieval benchmark.

Abstract

The computer vision and pattern recognition communities have recently witnessed a surge of feature-based methods in object recognition and image retrieval applications. These methods allow representing images as collections of “visual words” and treat them using text search approaches following the “bag of features” paradigm. In this article, we explore analogous approaches in the 3D world applied to the problem of nonrigid shape retrieval in large databases. Using multiscale diffusion heat kernels as “geometric words,” we construct compact and informative shape descriptors by means of the “bag of features” approach. We also show that considering pairs of “geometric words” (“geometric expressions”) allows creating spatially sensitive bags of features with better discriminative power. Finally, adopting metric learning approaches, we show that shapes can be efficiently represented as binary codes. Our approach achieves state-of-the-art results on the SHREC 2010 large-scale shape retrieval benchmark.