Di Yan

Google (United States), Tsinghua University

Papers

3

Total Citations

60

H-Index

2

About

Di Yan is a researcher at the forefront of 3D computer vision and intelligent robotic systems, with a primary focus on holistic 3D scene understanding and automated manufacturing. His most impactful contribution is the development of **FMGS (Foundation Model Embedded 3D Gaussian Splatting)** , a groundbreaking framework that integrates vision-language embeddings from foundation models directly into 3D Gaussian representations. This work, which has garnered over 42 citations since its 2024 release, enables precise, simultaneous perception of both geometric structure and semantic properties of real-world objects—a critical capability for advancing augmented reality and autonomous robotics. In parallel, Yan has made significant contributions to industrial automation, notably designing a robotic grinding system for friction stir weld seams. His 2020 paper on this topic introduced a novel monitoring method to prevent excessive grinding, which can damage base metals and incur substantial economic losses. By combining cutting-edge 3D scene understanding with practical robotic applications, Di Yan is bridging the gap between foundational AI research and real-world engineering challenges, positioning himself as an emerging leader in embodied AI and intelligent manufacturing.

Research Focus

Key Achievements

2
H-Index
3
Papers
60
Total Citations
20
Avg Citations/Paper
🏆 Most Cited Paper
FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding
42 citations · 2024
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: Google (United States), Tsinghua University

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago