MT-PCR: Hybrid Mamba-Transformer Network with Spatial Serialization for Point Cloud Registration

TL;DR

MT-PCR introduces a hybrid Mamba-Transformer framework with spatial serialization for efficient and accurate point cloud registration, overcoming computational limitations of traditional Transformer methods.

Contribution

This work is the first to integrate Mamba and Transformer modules with spatial serialization for point cloud registration, improving efficiency and accuracy.

Findings

Outperforms state-of-the-art methods in accuracy and efficiency.

Reduces GPU memory usage and FLOPs significantly.

Effectively models geometric structure of point clouds.

Abstract

Point cloud registration (PCR) is a fundamental task in 3D computer vision and robotics. Most learning-based PCR methods rely on Transformer architectures, which suffer from quadratic computational complexity. This limitation restricts the resolution of point clouds that can be processed, inevitably leading to information loss. In contrast, Mamba, a recently proposed model based on state-space models, achieves linear computational complexity while maintaining strong long-range contextual modeling capabilities. However, directly applying Mamba to PCR tasks yields suboptimal performance due to the unordered and irregular nature of point cloud data. To address these challenges, we propose MT-PCR, the first point cloud registration framework that integrates Mamba and Transformer modules. Specifically, we serialize point cloud features using Z-order space-filling curves to enforce spatial locality, enabling Mamba to better model the geometric structure of the inputs. Additionally, we remove the order-indicator module commonly used in Mamba-based sequence modeling, leading to improved performance in our setting. The serialized features are then processed by an optimized Mamba encoder, followed by a Transformer-based feature refinement stage. Extensive experiments on multiple benchmarks demonstrate that MT-PCR outperforms Transformer-based and other state-of-the-art methods in both accuracy and efficiency, significantly reducing GPU memory usage and FLOPs.