Boxiao Yu

University of Florida

Papers

3

Total Citations

56

H-Index

2

About

Boxiao Yu is an emerging researcher at the intersection of computer vision, deep learning, and autonomous underwater robotics. His work focuses on developing practical perception systems that enable low-cost, visually-guided robots to operate effectively in some of the most challenging aquatic environments on Earth. Yu's most significant contribution is UDepth, a fast monocular depth estimation pipeline that has garnered 47 citations since its 2023 publication. This work is particularly noteworthy for its novel end-to-end deep learning approach that incorporates domain-specific knowledge of underwater image formation — a critical advancement given how light scattering and attenuation distort visual data beneath the surface. By addressing these unique physical constraints, UDepth meaningfully advances 3D perception capabilities for resource-constrained underwater platforms. Beyond depth estimation, Yu has also tackled the highly specialized problem of autonomous cave mapping, developing weakly supervised methods for caveline detection to guide Autonomous Underwater Vehicles (AUVs) through submerged cave systems. This work has direct implications for water resource management and hydro-geological research. Yu's growing citation record reflects both the novelty and practical relevance of his contributions, making him a researcher worth following as underwater autonomy continues to mature as a field.

Research Focus

Key Achievements

2
H-Index
3
Papers
56
Total Citations
19
Avg Citations/Paper
🏆 Most Cited Paper
UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots
47 citations · 2023
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: University of Florida

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago