Instance by Instance: An Iterative Framework for Multi-Instance 3D Registration
Open Access
- 7 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (6) , 1117-1128
Abstract
Multi-instance registration is a challenging problem in computer vision and robotics, where multiple instances of an object need to be registered in a standard coordinate system. Pioneers followed a non-extensible one-shot framework, which prioritizes the registration of simple and isolated instances, often struggling to accurately register challenging or occluded instances. To address these challenges, we propose the first iterative framework for multi-instance 3D registration (MI-3DReg) in this work, termed instance-by-instance (IBI). It successively registers instances while systematically reducing outliers, starting from the easiest and progressing to more challenging ones. This enhances the likelihood of effectively registering instances that may have been initially overlooked, allowing for successful registration in subsequent iterations. Under the IBI framework, we further propose a sparse-to-dense correspondence-based multi-instance registration method (IBI-S2DC) to enhance the robustness of MI-3DReg. Experiments on both synthetic and real datasets have demonstrated the effectiveness of IBI and suggested the new state-of-the-art performance with IBI-S2DC, e.g., our mean registration F1 score is 12.02%/12.35% higher than the existing state-of-the-art on the synthetic/real datasets. The source codes are availableonline at https://github.com/caoxy01/IBI.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62372377)
This publication has 57 references indexed in Scilit:
- Sampling locally, hypothesis globally: accurate 3D point cloud registration with a RANSAC variantVisual Intelligence, 2023
- PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration2022
- Ranking 3D feature correspondences via consistency votingPattern Recognition Letters, 2019
- Multi-class Model Fitting by Energy Minimization and Mode-Seeking2018
- Local voxelized structure for 3D binary feature representation and robust registration of point clouds from low-cost sensorsInformation Sciences, 2018
- Fast Global Registration2016
- Going Further with Point Pair Features2016
- Point Pair Features Based Object Detection and Pose Estimation Revisited2015
- A Scale Independent Selection Process for 3D Object Recognition in Cluttered ScenesInternational Journal of Computer Vision, 2012
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004