An Indexing Scheme and Descriptor for 3D Object Retrieval Based on Local Shape Querying

TL;DR

This paper introduces a fast, clutter-resistant binary descriptor called QUICCI and an indexing scheme using Hamming trees for efficient 3D object retrieval based on local shape queries, demonstrating high effectiveness on large datasets.

Contribution

It presents a novel binary descriptor QUICCI and a Hamming tree indexing scheme, enabling efficient and robust 3D object retrieval from large datasets.

Findings

Effective retrieval on 828 million images from SHREC2017 dataset.

QUICCI's clutter resistance demonstrated through clutterbox experiment.

Fast comparison due to small binary descriptor size.

Abstract

A binary descriptor indexing scheme based on Hamming distance called the Hamming tree for local shape queries is presented. A new binary clutter resistant descriptor named Quick Intersection Count Change Image (QUICCI) is also introduced. This local shape descriptor is extremely small and fast to compare. Additionally, a novel distance function called Weighted Hamming applicable to QUICCI images is proposed for retrieval applications. The effectiveness of the indexing scheme and QUICCI is demonstrated on 828 million QUICCI images derived from the SHREC2017 dataset, while the clutter resistance of QUICCI is shown using the clutterbox experiment.