Open access
Sep 2026
An improved geometric priors-based indoor 3D object detection in point clouds for mobile robots
An efficient indoor 3D object detection model (Geo3D) is proposed, which exploits geometric priors to refine the feature learning pipeline and achieves superior performance compared to existing point cloud–based detection methods.
Jian-Jun Ni, Sheng-Ying Wu, Jie Liu et al.
· Measurement science and tech... · 0 citations