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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Existing point cloud modeling datasets primarily express the modelingprecision by pose or trajectory precision rather than the point cloud modelingeffect itself. Under this demand, we first independently construct a set ofLiDAR system with an optical stage, and then we build a HPMB dataset based onthe constructed LiDAR system, a High-Precision, Multi-Beam, real-world dataset.Second, we propose an modeling evaluation method based on HPMB for object-levelmodeling to overcome this limitation. In addition, the existing point cloudmodeling methods tend to generate continuous skeletons of the globalenvironment, hence lacking attention to the shape of complex objects. To tacklethis challenge, we propose a novel learning-based joint framework, DSMNet, forhigh-precision 3D surface modeling from sparse point cloud frames. DSMNetcomprises density-aware Point Cloud Registration (PCR) and geometry-aware PointCloud Sampling (PCS) to effectively learn the implicit structure feature ofsparse point clouds. Extensive experiments demonstrate that DSMNet outperformsthe state-of-the-art methods in PCS and PCR on Multi-View Partial Point Cloud(MVP) database. Furthermore, the experiments on the open source KITTI and ourproposed HPMB datasets show that DSMNet can be generalized as a post-processingof Simultaneous Localization And Mapping (SLAM), thereby improving modelingprecision in environments with sparse point clouds.

DSMNet: Deep High-precision 3D Surface Modeling from Sparse Point Cloud Frames