Jeonghyun Noh
Papers
1
Total Citations
7
H-Index
1
About
Jeonghyun Noh is a leading researcher in computer vision and autonomous systems, with a primary focus on depth completion—a critical technology for reconstructing dense 3D environmental information from sparse sensor data. His most influential work, the ADNet (Non-Local Affinity Distillation Network), introduced a novel framework for lightweight depth completion that leverages guidance from missing LiDAR points. This approach addresses a fundamental challenge in real-world applications like autonomous driving, robotics, and augmented reality, where computational efficiency and accuracy are paramount. ADNet has already garnered 7 citations since its 2024 publication, reflecting its immediate impact on the field. Noh’s contributions are particularly notable for their practical orientation: his models are designed to operate under strict real-time constraints while maintaining high fidelity in depth estimation. By combining non-local affinity mechanisms with knowledge distillation, he has advanced the state of the art in making deep learning models both compact and effective for resource-constrained environments. His work continues to shape how autonomous systems perceive and interact with their surroundings, bridging the gap between theoretical computer vision research and deployable engineering solutions.
Research Focus
Key Achievements
Top Papers
- 1