Longguang Wang

National University of Defense Technology, PLA Air Force Aviation University

Papers

Total Citations

H-Index

About

Longguang Wang is a leading researcher in 3D computer vision, with a focus on autonomous driving and robotic perception. His work centers on depth completion and panoptic segmentation, addressing critical challenges in how machines perceive and navigate complex outdoor environments. Wang’s most influential contribution is the development of SLFNet, an efficient stereo-LiDAR fusion network that achieves real-time, dense depth map prediction by synergistically combining the strengths of stereo images and LiDAR point clouds. This work has garnered 15 citations for its practical impact on autonomous systems. More recently, Wang has advanced the field of 3D panoptic segmentation with a novel approach that employs a Gaussian mixture model to overcome the traditional assumption that inter-instance differences always exceed intra-class variations. This 2024 paper, with 11 citations, offers a more nuanced and accurate method for parsing outdoor scenes, directly benefiting applications like autonomous driving and robot navigation. Through these contributions, Wang is shaping the future of reliable, real-time 3D scene understanding.