D3Former: jointly learning repeatable dense detectors and feature-enhanced descriptors via saliency-guided transformer

DOI10.1016/J.CAGD.2024.102300MaRDI QIDQ6563903zbMATH OpenFDO

Authors Junjie Gao, Pengfei Wang, Qiujie Dong, Qiong Zeng, Shiqing Xin, Caiming Zhang

Publication date 28 June 2024

Published in Computer Aided Geometric Design (Search for Journal in Brave)

zbMATH Keywords

point cloud registrationattention mechanismrepeatable keypoints

Mathematics Subject Classification ID

Numerical approximation and computational geometry (primarily algorithms) (65Dxx)

Recommendations

• CasViGE: Learning robust point cloud registration with cascaded visual-geometric encoding
• Point cloud registration using virtual interest points from Macaulay's resultant of quadric surfaces
• Efficient object recognition under cluttered scenes via descriptor-based matching and single point voting
• A robust estimation technique for 3D point cloud registration
• Efficient registration of multi-view point sets by K-means clustering

Cites work

• Concerning nonnegative matrices and doubly stochastic matrices

Cited in

(3)

• FPFNet: Fourier transform-based point cloud filter network for point cloud learning
• Outlier robust feature correspondence by learning based matching process
• Efficient object recognition under cluttered scenes via descriptor-based matching and single point voting

This page was built for publication: D3Former: jointly learning repeatable dense detectors and feature-enhanced descriptors via saliency-guided transformer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6563903)