Jianan Zhen

Papers

Total Citations

H-Index

About

Jianan Zhen is a rising researcher in computer vision and robotics, with a focus on advancing 6D object pose estimation and tracking. Their key research areas include zero-shot learning, monocular RGB-based perception, and 3D object understanding. Zhen’s major contribution is the development of "Zero6DOT," a pioneering framework for zero-shot 6D object pose tracking using only monocular RGB video—eliminating the need for CAD models, multi-modal sensors, or category-level priors. This work, published in 2025, has already garnered early citations, signaling its potential to transform applications in robotic manipulation and virtual reality by enabling robust, resource-efficient tracking in unseen environments. Zhen’s approach addresses a critical bottleneck in the field, where traditional methods rely heavily on pre-existing 3D models or depth data. Their research promises to democratize 6D tracking, making it accessible for real-world deployment. As a young scholar, Zhen’s innovative work marks a significant step toward more adaptive and scalable vision systems, positioning them as a notable contributor to the next generation of computer vision research.