Point Tree Transformer for Point Cloud Registration

TL;DR

The paper introduces Point Tree Transformer (PTT), a novel transformer-based method for point cloud registration that efficiently models local and global features with linear complexity, outperforming existing methods.

Contribution

It proposes a hierarchical feature tree and a new Point Tree Attention mechanism to focus on salient points, improving local structure modeling and computational efficiency.

Findings

Achieves superior registration accuracy on 3DMatch, ModelNet40, and KITTI datasets.

Maintains linear computational complexity while enhancing feature extraction.

Outperforms state-of-the-art methods in point cloud registration tasks.

Abstract

Point cloud registration is a fundamental task in the fields of computer vision and robotics. Recent developments in transformer-based methods have demonstrated enhanced performance in this domain. However, the standard attention mechanism utilized in these methods often integrates many low-relevance points, thereby struggling to prioritize its attention weights on sparse yet meaningful points. This inefficiency leads to limited local structure modeling capabilities and quadratic computational complexity. To overcome these limitations, we propose the Point Tree Transformer (PTT), a novel transformer-based approach for point cloud registration that efficiently extracts comprehensive local and global features while maintaining linear computational complexity. The PTT constructs hierarchical feature trees from point clouds in a coarse-to-dense manner, and introduces a novel Point Tree Attention (PTA) mechanism, which follows the tree structure to facilitate the progressive convergence of attended regions towards salient points. Specifically, each tree layer selectively identifies a subset of key points with the highest attention scores. Subsequent layers focus attention on areas of significant relevance, derived from the child points of the selected point set. The feature extraction process additionally incorporates coarse point features that capture high-level semantic information, thus facilitating local structure modeling and the progressive integration of multiscale information. Consequently, PTA empowers the model to concentrate on crucial local structures and derive detailed local information while maintaining linear computational complexity. Extensive experiments conducted on the 3DMatch, ModelNet40, and KITTI datasets demonstrate that our method achieves superior performance over the state-of-the-art methods.