4 papers
NCGR: Noise-Conditional Gated Rectification for Camera Extrinsic Perturbations in BEV 3D Object Detection
Wenbin Pan, Wanhao Liu, Liwei Luo +3
Camera-based bird's-eye-view (BEV) 3D detection typically assumes accurate and fixed camera extrinsics. In detectors using spatial cross-attention (SCA), extrinsic perturbations di…
PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
Xianjing Cheng, Lintai Wu, Zuowen Wang +3
Accurate 3D scene understanding in outdoor environments heavily relies on high-quality point clouds. However, LiDAR-scanned data often suffer from extreme sparsity, severely hinder…
Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learning
Lintai Wu, Xianjing Cheng, Yong Xu +2
In real-world scenarios, scanned point clouds are often incomplete due to occlusion issues. The tasks of self-supervised and weakly-supervised point cloud completion involve recons…
3D Shape Completion on Unseen Categories:A Weakly-supervised Approach
Lintai Wu, Junhui Hou, Linqi Song +1
3D shapes captured by scanning devices are often incomplete due to occlusion. 3D shape completion methods have been explored to tackle this limitation. However, most of these metho…