Yongyang Xu
Papers
1
Total Citations
3
H-Index
1
About
Yongyang Xu is a rising researcher in 3D computer vision, with a primary focus on large-scale point cloud semantic segmentation—a critical technology for autonomous driving, robotics, and virtual reality. His most notable contribution is the development of LACV-Net (Local Adaptive and Comprehensive VLAD Network), a novel architecture that addresses a fundamental challenge in the field: balancing computational efficiency with segmentation accuracy in massive point cloud scenes. While traditional methods rely on aggressive down-sampling that sacrifices fine-grained details, Xu’s work introduces a local adaptive mechanism combined with a comprehensive Vector of Locally Aggregated Descriptors (VLAD) to preserve spatial and semantic information without overwhelming computational resources. This innovation enables more precise scene understanding in real-world applications. Although early in his career, with his flagship paper accumulating 3 citations to date, Xu’s work represents a promising step toward scalable, high-fidelity 3D perception. His research sits at the intersection of geometric deep learning and efficient neural network design, offering practical solutions for systems that must interpret complex, unstructured environments in real time.
Research Focus
Key Achievements
Top Papers
- 1