Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent works improve training efficiency by decoupling SCR into a scene-agnostic backbone and scene-specific prediction heads, w...
Wen Li, Shang-Shu Yu, Dunqiang Liu et al.· 0 citations
LiDAR relocalization aims to estimate the global 6-DoF pose of a sensor in the environment. However, existing regression-based approaches often encounter limitations in dynamic or ambiguous scenarios, as they typically prioritize single-frame inference, leaving the potential of spatio-temporal consistency across scans...
Ming-Hang Zhu, Zhi-Jing Wang, Yu-Xin Guo et al.· 0 citations
Image-to-LiDAR registration estimates the camera pose of an image with respect to a LiDAR point cloud. It has diverse applications in autonomous driving, robot navigation etc. However, state-of-the-art (SOTA) methods still 1) mostly assume same-frame inputs, struggling with the image and point cloud from distant frames...
Zi-Jun Li, Xiao-Tian Sun, Xuelun Shen et al.· 0 citations
CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training, is proposed and Semantic Predictive Distillation is introduced to consolidate the student's semantic awareness in the feature space.
Kezheng Xiong, Shi-Yun Xu, Sheng Ao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
