Papers

1

Total Citations

15

H-Index

1

About

Dong-Uk Seo is a robotics researcher whose work centers on visual simultaneous localization and mapping (SLAM) and depth completion—critical technologies for autonomous navigation and 3D scene understanding. His most notable contribution, "Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities From Visual SLAM" (2022), addresses a fundamental limitation of feature-based visual SLAM: the sparsity of depth estimates. By introducing a mesh-refined, unsupervised depth completion method that exploits structural regularities from SLAM, Seo enables the generation of dense depth maps from sparse feature data—a breakthrough that bridges the gap between efficient feature tracking and the dense perception required for robust robotic operation. This work has already garnered 15 citations, reflecting its significance in the field. Seo’s research is particularly impactful for applications in autonomous driving, drone navigation, and mobile robotics, where accurate depth perception is essential. His innovative approach to combining SLAM with depth completion demonstrates a deep understanding of both geometric constraints and learning-based methods, positioning him as a rising contributor to the advancement of intelligent perception systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
15
Total Citations
15
Avg Citations/Paper
🏆 Most Cited Paper
Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities From Visual SLAM
15 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Korea Advanced Institute of Science and Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago