Chang Yuchen, Wang Kaiping
Department of Computer Science, Xi'an University of Architecture and Technology, Xi'an, 710055, Shaanxi Province, China.
Sci Rep. 2025 Jan 28;15(1):3570. doi: 10.1038/s41598-025-86704-6.
The attention mechanism has significantly progressed in various point cloud tasks. Benefiting from its significant competence in capturing long-range dependencies, research in point cloud completion has achieved promising results. However, the typically disordered point cloud data features complicated non-Euclidean geometric structures and exhibits unpredictable behavior. Most current attention modules are based on Euclidean or local geometry, which fails to accurately represent the intrinsic non-Euclidean characteristics of point cloud data. Thus, we propose a novel geodesic attention-based multi-stage refinement transformer network, which enables the alignment of feature dimensions among query, key, and value, and long-range geometric dependencies are captured on the manifold. Then, a novel Position Feature Extractor is designed to enhance geometric features and explicitly capture graph-based non-Euclidean properties of point cloud objects. A Recurrent Information Aggregation Unit is further applied to aggregate historical information from the previous stages and current geometric features to guide the network in the current stage. The proposed method exhibits strong competitiveness when compared to current state-of-the-art methods.
注意力机制在各种点云任务中取得了显著进展。受益于其在捕捉长距离依赖关系方面的显著能力，点云补全研究取得了令人鼓舞的成果。然而，典型的无序点云数据具有复杂的非欧几里得几何结构，并表现出不可预测的行为。当前大多数注意力模块基于欧几里得或局部几何，无法准确表示点云数据的内在非欧几里得特征。因此，我们提出了一种基于测地线注意力的新型多阶段细化Transformer网络，该网络能够实现查询、键和值之间特征维度的对齐，并在流形上捕捉长距离几何依赖关系。然后，设计了一种新型位置特征提取器来增强几何特征，并明确捕捉点云对象基于图的非欧几里得属性。进一步应用循环信息聚合单元来聚合来自前一阶段的历史信息和当前几何特征，以指导当前阶段的网络。与当前的最先进方法相比，所提出的方法具有很强的竞争力。
