Lahnet: Local Attentive Hashing Network For Point Cloud Registration

Abstract

Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for enhancing feature distinctiveness. In this paper, we propose a Local Attentive Hashing Network for point cloud registration, called LAHNet, which introduces a local attention mechanism with the inductive bias of locality of convolution-like operators into point cloud descriptors. Specifically, a Group Transformer is designed to capture reasonable long-range context between points. This employs a linear neighborhood search strategy, Locality-Sensitive Hashing, enabling uniformly partitioning point clouds into non-overlapping windows. Meanwhile, an efficient cross-window strategy is adopted to further expand the reasonable feature receptive field. Furthermore, building on this effective windowing strategy, we propose an Interaction Transformer to enhance

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyqu2025lahnet

Related papers

• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76
• Lpd-net: 3D Point Cloud Learning For Large-scale Place Recognition And Environment Analysis (2018)18.40
• PCAN: 3D Attention Map Learning Using Contextual Information For Point Cloud Based Retrieval (2019)17.42
• REGTR: End-to-end Point Cloud Correspondences With Transformers (2022)22.67
• Attributes Grouping And Mining Hashing For Fine-grained Image Retrieval (2023)10.07
• Deep Ordinal Hashing With Spatial Attention (2018)14.66
• Pointnetvlad: Deep Point Cloud Based Retrieval For Large-scale Place Recognition (2018)25.45
• Unsupervised Domain-adaptive Hash For Networks (2021)0.00