3 papers
cs.CV2025
LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures
Wenzhe He, Xiaojun Chen, Ruiqi Wang +5
3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models f…
cs.CV2025
RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion
Wenzhe He, Xiaojun Chen, Wentang Chen +3
Semantic Scene Completion (SSC) aims to generate a complete semantic scene from an incomplete input. Existing approaches often employ dense network architectures with a high parame…
cs.RO2025
NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection
Qingyu Fan, Yinghao Cai, Chao Li +5
Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information. In this paper, we introduce NeuGrasp,…