Riemann-based Multi-scale Attention Reasoning Network For Text-3d Retrieval

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,

Stats

• citations2
• S2 citations—
• github stars2
• HF likes0
• heat score4.53
• arxiv keyli2024riemann

Related papers

• Hyperbolic Hierarchical Alignment Reasoning Network For Text-3d Retrieval (2025)1.81
• Ri-mamba: Rotation-invariant Mamba For Robust Text-to-shape Retrieval (2026)0.00
• Enhanced Cross-modal 3D Retrieval Via Tri-modal Reconstruction (2025)0.00
• Transcending Fusion: A Multi-scale Alignment Method For Remote Sensing Image-text Retrieval (2024)11.92
• Exploring A Fine-grained Multiscale Method For Cross-modal Remote Sensing Image Retrieval (2022)16.73
• Sca-pvnet: Self-and-cross Attention Based Aggregation Of Point Cloud And Multi-view For 3D Object Retrieval (2023)10.07
• Cross-modal Implicit Relation Reasoning And Aligning For Text-to-image Person Retrieval (2023)18.15
• Remote Sensing Cross-modal Text-image Retrieval Based On Global And Local Information (2022)19.48