Guoqiang Feng
Papers
1
Total Citations
3
H-Index
1
About
Guoqiang Feng is a researcher advancing the frontier of 3D computer vision, with a primary focus on efficient and scalable semantic segmentation for large-scale point clouds. His most notable contribution, the development of LessNet, directly tackles the critical challenge of balancing computational efficiency with segmentation accuracy in outdoor environments. This lightweight architecture is designed to process the vast, irregular data generated by LiDAR sensors, making it highly relevant for real-world applications in autonomous driving and robotics. By proposing a method that significantly reduces model complexity without sacrificing performance, Feng addresses a key bottleneck in deploying deep learning models on resource-constrained platforms. While his highly-cited work on LessNet (with 3 citations) is still gaining recognition, its innovative approach to efficiency marks a meaningful step toward practical, real-time 3D perception. His research is poised to have a growing impact on systems that require rapid and reliable understanding of complex, large-scale spatial environments.
Research Focus
Key Achievements
Top Papers
- 1