Junjun Pan
Papers
3
Total Citations
71
H-Index
3
About
Junjun Pan is a leading researcher at the intersection of computer vision, virtual reality, and surgical robotics, with a focus on advancing minimally invasive medical procedures. His work primarily addresses two critical challenges in modern surgery: real-time 3D reconstruction and immersive surgical simulation. In his highly cited 2024 paper, "Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer" (40 citations), Pan pioneered a hybrid deep learning approach that enables accurate depth perception from endoscopic video without requiring ground-truth labels—a breakthrough for surgical navigation and pre-operative registration. This self-supervised method overcomes the data scarcity problem in medical imaging. Complementing this, his 2023 work on a "Virtual Reality Based Digital-Twin Robotic Minimally Invasive Surgery Simulator" (25 citations) created a novel platform that combines digital twin technology with VR to eliminate surgeon hand tremors and reduce patient trauma. Pan's contributions extend to multi-modality guidance systems for percutaneous endoscopic discectomy (2021), demonstrating his commitment to translating computational innovations into tangible clinical tools. His research, consistently cited for its practical impact, is shaping the future of safer, more precise robotic surgery.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3