no code implementations • 17 Dec 2023 • Boming Zhao, Luwei Yang, Mao Mao, Hujun Bao, Zhaopeng Cui
In this paper, we propose a novel visual localization framework, \ie, PNeRFLoc, based on a unified point-based representation.
no code implementations • ICCV 2023 • Chaoran Tian, Weihong Pan, Zimo Wang, Mao Mao, Guofeng Zhang, Hujun Bao, Ping Tan, Zhaopeng Cui
Stereo depth estimation usually struggles to deal with textureless scenes for both traditional and learning-based methods due to the inherent dependence on image correspondence matching.