Xiuling Wang

Shandong University of Science and Technology

Papers

Total Citations

H-Index

About

Xiuling Wang is a rising researcher in computer vision, with a focused expertise in self-supervised monocular depth estimation—a critical technology for autonomous driving and robot navigation. Her work addresses the fundamental challenge of inferring 3D scene information from a single camera, a task far more difficult than stereo-based approaches but essential for real-world deployment. Wang's major contributions include pioneering the integration of direct methods into self-supervised frameworks, as demonstrated in her 2020 paper (15 citations), which improved depth prediction accuracy without requiring ground-truth labels. She further advanced the field by modeling high-order spatial interactions (2024, 5 citations) to capture complex scene geometry, and by incorporating semantic guidance (2022, 4 citations) to enhance depth estimation in diverse environments. Her research consistently pushes the boundaries of what is achievable with monocular video data, offering practical solutions for vision-related tasks in robotics and autonomous systems. With a growing citation record and a clear trajectory of innovation, Xiuling Wang is establishing herself as a key contributor to self-supervised learning in 3D perception.