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

doi:doi:10.57702/o74q6u5j

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.

BibTex:

@dataset{Hao_Yu_and_Ji_Hou_and_Zheng_Qin_and_Mahdi_Saleh_and_Ivan_Shugurov_and_Kai_Wang_and_Benjamin_Busam_and_Slobodan_Ilic_2024,
    abstract = {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.},
    author = {Hao Yu and Ji Hou and Zheng Qin and Mahdi Saleh and Ivan Shugurov and Kai Wang and Benjamin Busam and Slobodan Ilic},
    doi = {10.57702/o74q6u5j},
    institution = {No Organization},
    keyword = {'globally-aware', 'point cloud registration', 'rotation-invariant'},
    month = {dec},
    publisher = {TIB},
    title = {RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration},
    url = {https://service.tib.eu/ldmservice/dataset/riga--rotation-invariant-and-globally-aware-descriptors-for-point-cloud-registration},
    year = {2024}
}