Dae Woong
Papers
1
Total Citations
2
H-Index
1
About
Dae Woong is a researcher in computer vision and autonomous driving, with a particular focus on monocular 3D object detection—a challenging task that requires inferring depth and spatial relationships from a single camera image. His most notable contribution, "MonoDGAE: depth-guided attention and bilateral filtering for robust monocular 3D object detection" (2025), introduces a novel architecture that leverages depth-guided attention mechanisms and bilateral filtering to improve detection accuracy and robustness. This work addresses key limitations in existing methods, such as depth ambiguity and noisy predictions, by integrating geometric priors with learned attention. Although early in its citation trajectory with 2 citations, MonoDGAE represents a promising step toward safer and more reliable perception systems for autonomous vehicles. Dae Woong’s research bridges the gap between 2D image understanding and 3D scene reconstruction, offering practical solutions for real-world deployment. His work is particularly relevant for students and researchers interested in the intersection of deep learning, geometric reasoning, and robotics.
Research Focus
Key Achievements
Top Papers
- 1