Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes

TL;DR

This paper introduces MIRETR, a transformer-based method for multi-instance point cloud registration that improves accuracy in cluttered scenes by learning instance-aware features and masks, significantly outperforming existing methods.

Contribution

The work presents a novel coarse-to-fine framework that extracts instance-aware correspondences, addressing the challenge of background and inter-instance interference in cluttered scenes.

Findings

Outperforms state-of-the-art by 16.6 points on F1 score on ROBI benchmark.

Effective in cluttered scenes with multiple instances.

Demonstrates robustness and high accuracy in public benchmarks.

Abstract

Multi-instance point cloud registration estimates the poses of multiple instances of a model point cloud in a scene point cloud. Extracting accurate point correspondence is to the center of the problem. Existing approaches usually treat the scene point cloud as a whole, overlooking the separation of instances. Therefore, point features could be easily polluted by other points from the background or different instances, leading to inaccurate correspondences oblivious to separate instances, especially in cluttered scenes. In this work, we propose MIRETR, Multi-Instance REgistration TRansformer, a coarse-to-fine approach to the extraction of instance-aware correspondences. At the coarse level, it jointly learns instance-aware superpoint features and predicts per-instance masks. With instance masks, the influence from outside of the instance being concerned is minimized, such that highly reliable superpoint correspondences can be extracted. The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks. At last, an efficient candidate selection and refinement algorithm is devised to obtain the final registrations. Extensive experiments on three public benchmarks demonstrate the efficacy of our approach. In particular, MIRETR outperforms the state of the arts by 16.6 points on F1 score on the challenging ROBI benchmark. Code and models are available at https://github.com/zhiyuanYU134/MIRETR.