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

Establishing accurate and representative matches is a crucial step inaddressing the point cloud registration problem. A commonly employed approachinvolves detecting keypoints with salient geometric features and subsequentlymapping these keypoints from one frame of the point cloud to another. However,methods within this category are hampered by the repeatability of the sampledkeypoints. In this paper, we introduce a saliency-guided trans\textbf{former},referred to as \textit{D3Former}, which entails the joint learning ofrepeatable \textbf{D}ense \textbf{D}etectors and feature-enhanced\textbf{D}escriptors. The model comprises a Feature Enhancement DescriptorLearning (FEDL) module and a Repetitive Keypoints Detector Learning (RKDL)module. The FEDL module utilizes a region attention mechanism to enhancefeature distinctiveness, while the RKDL module focuses on detecting repeatablekeypoints to enhance matching capabilities. Extensive experimental results onchallenging indoor and outdoor benchmarks demonstrate that our proposed methodconsistently outperforms state-of-the-art point cloud matching methods.Notably, tests on 3DLoMatch, even with a low overlap ratio, show that ourmethod consistently outperforms recently published approaches such as RoReg andRoITr. For instance, with the number of extracted keypoints reduced to 250, theregistration recall scores for RoReg, RoITr, and our method are 64.3\%, 73.6\%,and 76.5\%, respectively.

D3Former: Jointly Learning Repeatable Dense Detectors and Feature-enhanced Descriptors via Saliency-guided Transformer