LAHNet: Local Attentive Hashing Network for Point Cloud Registration
This work addresses the challenge of feature distinctiveness in point cloud registration for applications like robotics and autonomous driving, representing an incremental improvement over existing methods.
The paper tackles the problem of generating distinctive features for point cloud registration by proposing LAHNet, which introduces a local attention mechanism with a Group Transformer and Interaction Transformer to capture long-range context and enhance feature interactions in overlap regions, achieving significant registration results on real-world indoor and outdoor benchmarks.
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 the feature interactions of the overlap regions within point cloud pairs. This computes an overlap matrix to match overlap regions between point cloud pairs by representing each window as a global signal. Extensive results demonstrate that LAHNet can learn robust and distinctive features, achieving significant registration results on real-world indoor and outdoor benchmarks.