Papers
1
Total Citations
20
H-Index
1
About
Se-Ho Kim is a leading researcher in computer vision and robotics, whose work focuses on enabling robust perception in dynamic, real-world environments. His major contributions lie at the intersection of visual odometry, 3D geometry estimation, and semantic scene understanding. Kim is best known for developing the SimVODIS++ framework, a seminal approach that integrates neural semantic segmentation with visual odometry to overcome the critical challenge of performance degradation caused by moving objects—a persistent hurdle for autonomous vehicles and mobile robots. This work, published in 2022 and already accumulating over 20 citations, demonstrates his ability to solve practical problems by fusing geometric accuracy with high-level scene semantics. His research has significant implications for safe navigation in unpredictable settings, pushing beyond the limitations of traditional methods that assume static scenes. By bridging the gap between low-level motion estimation and high-level object awareness, Kim’s innovations are paving the way for more intelligent and reliable autonomous systems. His contributions are increasingly recognized as foundational for next-generation robotics and self-driving technology.
Research Focus
Key Achievements
Top Papers
- 1SimVODIS++: Neural Semantic Visual Odometry in Dynamic Environments20 citations · 2022