Juhui Lee
Papers
2
Total Citations
21
H-Index
2
About
Juhui Lee is a researcher specializing in computational imaging, depth estimation, and vision enhancement for challenging environments. Their work sits at the intersection of deep learning, computer vision, and robotics perception, with a particular focus on developing innovative solutions for degraded visual conditions such as underwater scenes and hazy environments. Lee's most notable contribution, "Joint-ID" (2023), introduces a transformer-based architecture that simultaneously performs image enhancement and depth estimation for underwater environments — a significant advancement given the inherent difficulties posed by light scattering, absorption, and turbulence in aquatic settings. This joint-learning approach has garnered 19 citations, reflecting strong community interest in unified frameworks that address multiple vision challenges concurrently. Complementing this work, Lee has also explored sparse depth-guided image enhancement through incremental Gaussian Processes, offering a practical dehazing solution tailored for robotics platforms where only sparse range measurements are available. This research demonstrates a thoughtful understanding of real-world deployment constraints often overlooked in purely academic settings. Together, Lee's contributions highlight a commitment to bridging theoretical computer vision advances with practical, sensor-aware applications, making their work particularly relevant for researchers working on autonomous systems, marine robotics, and real-world perception under adverse conditions.
Research Focus
Key Achievements
Top Papers
- 1
- 2