You're currently viewing an old version of this dataset. To see the current version, click here.

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive.

Data and Resources

Cite this as

Hao Yu, Ji Hou, Zheng Qin, Mahdi Saleh, Ivan Shugurov, Kai Wang, Benjamin Busam, Slobodan Ilic (2024). Dataset: RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration. https://doi.org/10.57702/o74q6u5j

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2209.13252
Author Hao Yu
More Authors
Ji Hou
Zheng Qin
Mahdi Saleh
Ivan Shugurov
Kai Wang
Benjamin Busam
Slobodan Ilic