Xuan Shao
Papers
1
Total Citations
1
H-Index
1
About
Xuan Shao is a researcher specializing in computer vision and deep learning, with a particular focus on self-supervised depth estimation for autonomous systems. Their most notable contribution is the development of LiDUT-Depth, a lightweight self-supervised depth estimation model that introduces dynamic upsampling and triplet loss optimization to achieve high accuracy with minimal computational overhead. This work, published in 2024, has already garnered attention in the field, demonstrating Shao's ability to address critical challenges in real-time perception for robotics and autonomous driving. By prioritizing efficiency without sacrificing performance, Shao's research offers practical solutions for resource-constrained environments, making depth estimation more accessible for embedded systems. Their work reflects a commitment to bridging the gap between theoretical advancements and real-world deployment, positioning them as an emerging voice in the intersection of efficient neural network design and 3D scene understanding. Shao's ongoing contributions continue to inspire researchers seeking to optimize deep learning models for practical, high-impact applications.
Research Focus
Key Achievements
Top Papers
- 1