Lingxuan Wang

Papers

Total Citations

H-Index

About

Lingxuan Wang is a leading researcher in computer vision and autonomous perception, with a primary focus on depth completion and 3D scene understanding. Their most influential work, "DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network" (2021), has garnered 57 citations and addresses a critical challenge in autonomous systems: generating dense, accurate depth maps from sparse LiDAR data. Wang’s key contribution lies in developing a novel pseudo-dense depth guidance mechanism that significantly improves depth completion quality while maintaining real-time performance—a vital requirement for self-driving vehicles and robotics. By tackling the inherent sparsity of input data and low-density ground truth, Wang’s approach enables more reliable 3D environmental perception, directly impacting safety and efficiency in autonomous navigation. This work stands as a notable achievement in bridging the gap between sparse sensor inputs and dense scene reconstruction, offering a practical solution for real-world deployment. Wang’s research continues to push the boundaries of depth estimation, making them a pivotal figure in advancing perception systems for intelligent machines.