Research Interests
3D laser scanning has been successfully applied to document surface conditions and model the actual geometrical dimensions of urban architectures, due to its capacity for automated, efficient, and high-density point acquisition. Large-scale point cloud processing and analysis have important research value for urban construction and structural health monitoring. With the rapid development of deep learning, combining point cloud processing and deep learning technology has become a major trend in the field of computer graphics.
My research interests mainly focus on point cloud processing and understanding, such as 3D object detection, point cloud segmentation and reconstruction, which can be applied to various fields like urban modeling, structure inspection and autonomous driving.
Education
- MSc, College of Mechanical Electrical Engineering, Nanjing University of Aeronautics and Astronautics, 2021
- BSc, College of Mechanical Electrical Engineering, Nanjing University of Aeronautics and Astronautics, 2018
Publications
- Dening Lu, Xuequan Lu, Yangxing Sun, et al. Deep Feature-Preserving Normal Estimation for Point Cloud Filtering, Computer Aided Design, 2020: 102860, presented in SPM 2020.
- Qian Xie, Dening Lu, et al. Aircraft Skin Rivet Detection Based on 3D Point Cloud via Multiple Structures Fitting, Computer Aided Design, 2020, 120: 102805.
- Cheng Yi, Dening Lu, et al. Hierarchical Tunnel Modeling from 3D Raw LiDAR Point Cloud, Computer Aided Design, 2019, 114: 143-154. presented in SPM 2019.
- Qian Xie, Dening Lu, et al. RRCNet: Rivet Region Classification Network for Rivet flush Measurement Based on 3D Point Cloud, IEEE Transactions on Instrumentation and Measurement, accepted in 2020.09.25.
- Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Dening Lu, Mingqiang Wei and Jun Wang. VENet: Voting Enhancement Network for 3D Object Detection, accepted by 2021 IEEE/CVF International Conference on Computer Vision (ICCV).