Deep-PE: A Learning-Based Pose Evaluator for Point Cloud Registration

Simple item page
dc.contributor.authorGao, Junjieen_US
dc.contributor.authorWang, Chongjianen_US
dc.contributor.authorDing, Zhongjunen_US
dc.contributor.authorChen, Shuangminen_US
dc.contributor.authorXin, Shiqingen_US
dc.contributor.authorTu, Changheen_US
dc.contributor.authorWang, Wenpingen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:03:19Z
dc.date.available2024-10-13T18:03:19Z
dc.date.issued2024
dc.description.abstractIn the realm of point cloud registration, the most prevalent pose evaluation approaches are statistics-based, identifying the optimal transformation by maximizing the number of consistent correspondences. However, registration recall decreases significantly when point clouds exhibit a low overlap ratio, despite efforts in designing feature descriptors and establishing correspondences. In this paper, we introduce Deep-PE, a lightweight, learning-based pose evaluator designed to enhance the accuracy of pose selection, especially in challenging point cloud scenarios with low overlap. Our network incorporates a Pose-Aware Attention (PAA) module to simulate and learn the alignment status of point clouds under various candidate poses, alongside a Pose Confidence Prediction (PCP) module that predicts the likelihood of successful registration. These two modules facilitate the learning of both local and global alignment priors. Extensive tests across multiple benchmarks confirm the effectiveness of Deep-PE. Notably, on 3DLoMatch with a low overlap ratio, Deep-PE significantly outperforms state-of-the-art methods by at least 8% and 11% in registration recall under handcrafted FPFH and learning-based FCGF descriptors, respectively. To the best of our knowledge, this is the first study to utilize deep learning to select the optimal pose without the explicit need for input correspondences.en_US
dc.description.sectionheadersPoint Cloud Processing and Analysis I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241278
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages15 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241278
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241278
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Matching
dc.subjectComputing methodologies → Matching
dc.titleDeep-PE: A Learning-Based Pose Evaluator for Point Cloud Registrationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241278.pdf
Size:
3.2 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters