Jiongqi Qu

Papers

Total Citations

H-Index

About

Jiongqi Qu is a leading researcher at the intersection of computer vision and robotic-assisted surgery (RAS), with a primary focus on depth estimation and 3D reconstruction for minimally invasive procedures. Their most notable contribution is the development of DARES (Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model), a groundbreaking 2025 work that has already garnered 4 citations. This innovation addresses a critical challenge in surgical robotics: while foundation models like Depth Anything Models (DAM) excel in general scenes, they perform poorly in the unique, constrained environment of endoscopic surgery. Qu demonstrated that fully fine-tuning such models on limited surgical data leads to catastrophic forgetting, and instead introduced a self-supervised Vector-LoRA approach that adapts the foundation model efficiently without sacrificing its pre-trained knowledge. This work has significant implications for improving surgical visualization, enabling more accurate 3D reconstruction during robotic procedures. Qu’s research is characterized by its practical impact on clinical robotics, bridging the gap between state-of-the-art AI and real-world surgical needs. Their contributions are shaping the future of autonomous and semi-autonomous surgical systems, making them a rising figure in medical robotics and computer vision.