Jinfeng Liu

Papers

Total Citations

H-Index

About

Jinfeng Liu is a rising researcher at the intersection of robotic perception and medical robotics, with key contributions in self-supervised depth estimation and surgical automation. In his most-cited work, "Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation" (2023, 13 citations), Liu tackles a critical challenge in robotic perception: enabling depth estimation without expensive ground-truth annotations. His research advances self-supervised methods that more effectively leverage available data, improving how robots perceive and navigate their environments—a fundamental capability for autonomous systems. Liu also demonstrates innovative applications of computer vision in medicine, notably in "Follicular Unit Registration Based on Binocular Stereo Vision for Hair Transplantation Surgery Robot" (2023, 2 citations). Here, he addresses the difficult problem of registering visually similar follicular units using YOLOv5-based detection and stereo vision, enabling precise robotic hair transplantation. This work showcases his ability to adapt state-of-the-art deep learning techniques to real-world surgical challenges. While early in his career, Liu’s dual focus on foundational perception methods and translational medical robotics positions him as a promising contributor to both fields, with potential for significant future impact as his citation counts grow.