English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Point cloud registration is a task to estimate the rigid transformationbetween two unaligned scans, which plays an important role in many computervision applications. Previous learning-based works commonly focus on supervisedregistration, which have limitations in practice. Recently, with the advance ofinexpensive RGB-D sensors, several learning-based works utilize RGB-D data toachieve unsupervised registration. However, most of existing unsupervisedmethods follow a cascaded design or fuse RGB-D data in a unidirectional manner,which do not fully exploit the complementary information in the RGB-D data. Toleverage the complementary information more effectively, we propose a networkimplementing multi-scale bidirectional fusion between RGB images and pointclouds generated from depth images. By bidirectionally fusing visual andgeometric features in multi-scales, more distinctive deep features forcorrespondence estimation can be obtained, making our registration moreaccurate. Extensive experiments on ScanNet and 3DMatch demonstrate that ourmethod achieves new state-of-the-art performance. Code will be released athttps://github.com/phdymz/PointMBF

PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration