3D Shape Knowledge Graph for Cross-domain 3D Shape Retrieval

TL;DR

This paper introduces a novel 3D shape knowledge graph using geometric words as nodes, enabling effective cross-domain and cross-modal 3D shape retrieval with superior performance on multiple datasets.

Contribution

The study proposes a new geometric word-based knowledge graph and a graph embedding method to improve cross-domain and cross-modal 3D shape retrieval.

Findings

Outperforms state-of-the-art methods on ModelNet40 and ShapeNetCore55 datasets.

Effective in cross-domain 3D shape retrieval tasks.

Demonstrates superiority in cross-modal retrieval on MI3DOR dataset.

Abstract

The surge in 3D modeling has led to a pronounced research emphasis on the field of 3D shape retrieval. Numerous contemporary approaches have been put forth to tackle this intricate challenge. Nevertheless, effectively addressing the intricacies of cross-modal 3D shape retrieval remains a formidable undertaking, owing to inherent modality-based disparities. This study presents an innovative notion, termed "geometric words", which functions as elemental constituents for representing entities through combinations. To establish the knowledge graph, we employ geometric words as nodes, connecting them via shape categories and geometry attributes. Subsequently, we devise a unique graph embedding method for knowledge acquisition. Finally, an effective similarity measure is introduced for retrieval purposes. Importantly, each 3D or 2D entity can anchor its geometric terms within the knowledge graph, thereby serving as a link between cross-domain data. As a result, our approach facilitates multiple cross-domain 3D shape retrieval tasks. We evaluate the proposed method's performance on the ModelNet40 and ShapeNetCore55 datasets, encompassing scenarios related to 3D shape retrieval and cross-domain retrieval. Furthermore, we employ the established cross-modal dataset (MI3DOR) to assess cross-modal 3D shape retrieval. The resulting experimental outcomes, in conjunction with comparisons against state-of-the-art techniques, clearly highlight the superiority of our approach.