Yun Yue
Papers
1
Total Citations
9
H-Index
1
About
Yun Yue is a researcher at the forefront of computer vision and autonomous systems, with a primary focus on monocular depth estimation—a critical challenge for self-driving cars, robotics, and driving safety. Her most influential work, "Novel Hybrid Neural Network for Dense Depth Estimation using On-Board Monocular Images" (2020, 9 citations), tackles the ill-posed problem of inferring 3D depth from single 2D images. Yue's key contribution lies in designing a hybrid neural architecture that efficiently captures global contextual information, overcoming the inherent ambiguity of monocular depth prediction. This innovation directly addresses a tight bottleneck in autonomous perception: how to obtain dense, accurate depth maps without expensive LiDAR or stereo setups. By integrating convolutional networks with global reasoning mechanisms, her approach enhances both the robustness and computational efficiency of depth estimation for real-time on-board applications. Yue's work has been recognized as a stepping stone for safer automated driving systems, demonstrating that even with limited data, hybrid models can bridge the gap between 2D imagery and 3D scene understanding. Her research continues to inspire advances in depth-aware perception for intelligent vehicles and robotic navigation.
Research Focus
Key Achievements
Top Papers
- 1