Gyeong-Min Lee
Papers
1
Total Citations
9
H-Index
1
About
Gyeong-Min Lee is a rising researcher in computer vision, specializing in self-supervised learning for monocular depth estimation—a critical area for autonomous systems and 3D scene understanding. His most-cited work, "Revisiting Self-supervised Monocular Depth Estimation" (2022, 9 citations), offers a systematic re-evaluation of existing methods, identifying key architectural and training improvements that enhance depth prediction accuracy without requiring labeled data. This contribution addresses a fundamental challenge in robotics and augmented reality: enabling machines to perceive depth from single images in dynamic, real-world environments. Lee’s research bridges theory and practice, refining loss functions and network designs to boost performance on benchmarks like KITTI. While early in his career, his work has already garnered attention for its clarity and practical impact, providing a foundation for future advances in self-supervised depth learning. By demystifying the mechanisms behind successful monocular depth estimation, Lee empowers other researchers to build more robust, efficient models—a vital step toward fully autonomous perception.
Research Focus
Key Achievements
Top Papers
- 1Revisiting Self-supervised Monocular Depth Estimation9 citations · 2022