# Non-rigid 3D shape retrieval based on multi-view metric learning

## TL;DR

This paper introduces a multi-view metric learning algorithm for non-rigid 3D shape retrieval, leveraging intrinsic shape descriptors and extending MFA with HSCI to improve retrieval accuracy.

## Contribution

It proposes a novel multi-view metric learning method that jointly learns metrics for multiple intrinsic shape representations using MFA and HSCI, enhancing retrieval performance.

## Key findings

- Outperforms state-of-the-art methods on SHREC'10 benchmarks
- Effectively reduces redundancy between multiple shape representations
- Improves accuracy of non-rigid 3D shape retrieval

## Abstract

This study presents a novel multi-view metric learning algorithm, which aims to improve 3D non-rigid shape retrieval. With the development of non-rigid 3D shape analysis, there exist many shape descriptors. The intrinsic descriptors can be explored to construct various intrinsic representations for non-rigid 3D shape retrieval task. The different intrinsic representations (features) focus on different geometric properties to describe the same 3D shape, which makes the representations are related. Therefore, it is possible and necessary to learn multiple metrics for different representations jointly. We propose an effective multi-view metric learning algorithm by extending the Marginal Fisher Analysis (MFA) into the multi-view domain, and exploring Hilbert-Schmidt Independence Criteria (HSCI) as a diversity term to jointly learning the new metrics. The different classes can be separated by MFA in our method. Meanwhile, HSCI is exploited to make the multiple representations to be consensus. The learned metrics can reduce the redundancy between the multiple representations, and improve the accuracy of the retrieval results. Experiments are performed on SHREC'10 benchmarks, and the results show that the proposed method outperforms the state-of-the-art non-rigid 3D shape retrieval methods.