# SGRTmreg: A Learning-Based Optimization Framework for Multiple Pairwise Registrations

## TL;DR

This paper introduces SGRTmreg, a new framework that combines learning-based optimization and deep learning to improve the accuracy and robustness of multiple point cloud registrations.

## Contribution

The novel SGRTmreg framework integrates a searching scheme, GRDO optimization, and a transfer module for efficient and robust multi-instance point cloud registration.

## Key findings

- SGRTmreg outperforms state-of-the-art methods in registration accuracy and robustness.
- The framework achieves stable performance under noise, outliers, and occlusions.
- Experiments on multiple datasets confirm the effectiveness of the proposed approach.

## Abstract

Point cloud registration is a fundamental task in computer vision and graphics, which is widely used in 3D reconstruction, object tracking, and atlas reconstruction. Learning-based optimization and deep learning methods have been widely developed in pairwise registration due to their own distinctive advantages. Deep learning methods offer greater flexibility and enable registering unseen point clouds that are not trained. Learning-based optimization methods exhibit enhanced robustness and stability when handling registration under various perturbations, such as noise, outliers, and occlusions. To leverage the strengths of both approaches to achieve a less time-consuming, robust, and stable registration for multiple instances, we propose a novel computational framework called SGRTmreg for multiple pairwise registrations in this paper. The SGRTmreg framework utilizes three components—a Searching scheme, a learning-based optimization method called Graph-based Reweighted discriminative optimization (GRDO), and a Transfer module to achieve multi-instance point cloud registration.Given a collection of instances to be matched, a template as a target point cloud, and an instance as a source point cloud, the searching scheme selects one point cloud from the collection that closely resembles the source. GRDO then learns a sequence of regressors by aligning the source to the target, while the transfer module stores and applies the learned regressors to align the selected point cloud to the target and estimate the transformation of the selected point cloud. In short, SGRTmreg harnesses a shared sequence of regressors to register multiple point clouds to a target point cloud. We conduct extensive registration experiments on various datasets to evaluate the proposed framework. The experimental results demonstrate that SGRTmreg achieves multiple pairwise registrations with higher accuracy, robustness, and stability than the state-of-the-art deep learning and traditional registration methods.