Papers
1
Total Citations
15
H-Index
1
About
Yehao Sun is a researcher whose work lies at the intersection of computer vision and self-supervised learning, with a particular focus on monocular depth estimation. His most-cited paper, "Self-supervised monocular depth estimation with direct methods" (2020), has garnered 15 citations and represents a significant contribution to the field by integrating direct photometric methods into self-supervised frameworks. This approach enables more robust depth prediction from single images without requiring labeled ground-truth data, addressing a key challenge in autonomous driving and robotics. Sun’s work demonstrates how combining classical geometric constraints with modern deep learning can improve both accuracy and efficiency in 3D scene understanding. While his citation count is still growing, his research is notable for bridging traditional and contemporary techniques, offering a practical pathway for deploying depth estimation in real-world applications where labeled data is scarce. For students and researchers exploring self-supervised vision, Sun’s work provides a clear example of how to leverage geometric priors to enhance learning without supervision, making it a valuable reference for those interested in efficient, label-free perception systems.
Research Focus
Key Achievements
Top Papers
- 1Self-supervised monocular depth estimation with direct methods15 citations · 2020