Jianping Shi

Papers

Total Citations

241

H-Index

About

Jianping Shi is a leading researcher in computer vision, with a primary focus on 3D scene understanding, camera re-localization, and segmentation of challenging objects. Her work addresses critical problems in robotics, autonomous driving, and augmented reality. Shi’s most influential contribution is **CamNet** (2019, 138 citations), a coarse-to-fine retrieval framework that revolutionized camera re-localization by enabling robust, scene-agnostic pose estimation—a key enabler for mobile robots and AR devices. She also pioneered **Enhanced Boundary Learning for Glass-like Object Segmentation** (2021, 103 citations), tackling the notoriously difficult task of segmenting transparent and reflective surfaces like windows and mirrors. This work is vital for safe robot navigation and manipulation in complex environments. With over 240 citations across her top papers, Shi’s research consistently bridges the gap between theoretical computer vision and real-world deployment. Her boundary-learning techniques have been adopted in autonomous driving pipelines to prevent collisions with glass obstacles, and her re-localization methods are foundational for large-scale AR applications. Shi’s work exemplifies how precise, problem-driven research can directly impact practical systems.