Riemann-based Multi-scale Attention Reasoning Network for Text-3D Retrieval

TL;DR

This paper introduces a novel Riemann-based multi-scale attention network for text-3D retrieval, addressing data scarcity and complex geometric structures, and demonstrates superior performance on a newly created large-scale dataset.

Contribution

The paper proposes the RMARN model with Riemann attention and new dataset T3DR-HIT for effective text-3D retrieval, overcoming data and geometric complexity challenges.

Findings

RMARN outperforms existing methods on T3DR-HIT dataset

Introduces Riemann attention mechanism for geometric data

Creates a large-scale Text-3D retrieval dataset

Abstract

Due to the challenges in acquiring paired Text-3D data and the inherent irregularity of 3D data structures, combined representation learning of 3D point clouds and text remains unexplored. In this paper, we propose a novel Riemann-based Multi-scale Attention Reasoning Network (RMARN) for text-3D retrieval. Specifically, the extracted text and point cloud features are refined by their respective Adaptive Feature Refiner (AFR). Furthermore, we introduce the innovative Riemann Local Similarity (RLS) module and the Global Pooling Similarity (GPS) module. However, as 3D point cloud data and text data often possess complex geometric structures in high-dimensional space, the proposed RLS employs a novel Riemann Attention Mechanism to reflect the intrinsic geometric relationships of the data. Without explicitly defining the manifold, RMARN learns the manifold parameters to better represent the distances between text-point cloud samples. To address the challenges of lacking paired text-3D data, we have created the large-scale Text-3D Retrieval dataset T3DR-HIT, which comprises over 3,380 pairs of text and point cloud data. T3DR-HIT contains coarse-grained indoor 3D scenes and fine-grained Chinese artifact scenes, consisting of 1,380 and over 2,000 text-3D pairs, respectively. Experiments on our custom datasets demonstrate the superior performance of the proposed method. Our code and proposed datasets are available at \url{https://github.com/liwrui/RMARN}.