Papers
2
Total Citations
7
H-Index
2
About
Fang Xu is an emerging researcher specializing in computer vision, deep learning, and robotic perception, with a particular focus on applying advanced neural network architectures to industrial automation challenges. Their work centers on two cutting-edge areas: 3D point cloud processing and depth image analysis for robotic applications. In their 2023 paper, Xu introduced C-LFNet, a Central-Local Feature Network designed to tackle the complex problem of 3D point cloud instance segmentation in robot bin-picking scenarios — a critical capability for enabling robots to identify and manipulate objects in cluttered industrial environments. Building on this foundation, Xu's 2024 work on DGConv presents a novel convolutional neural network approach specifically engineered to improve the recognition and segmentation of weld seam depth images during robotic intelligent operations, addressing longstanding limitations in geometric feature extraction from depth data. Together accumulating 7 citations across just two years, Xu's research demonstrates a consistent drive to bridge the gap between theoretical deep learning advances and real-world robotic deployment. Their contributions are particularly valuable for researchers and engineers working at the intersection of industrial robotics, intelligent manufacturing, and 3D scene understanding.
Research Focus
Key Achievements
Top Papers
- 1
- 2