Welcome to the Foundational Vision Laboratory (FoV Lab)

The Foundational Vision Laboratory (FoV Lab) is affiliated with the Graduate School of Advanced Imaging Science, Multimedia & Film (GSAIM) at Chung-Ang University (CAU) in Seoul, Korea.
FoV Lab explores the fundamental principles that enable intelligent visual systems to perceive, understand, and interact with the world.

Our mission is to develop generalizable, data-efficient, and human-aligned AI models. We tackle core challenges in visual perception, domain adaptation, multi-modal understanding, and human-AI collaboration.

We aim to build systems that:

• learn effectively from limited data,
• adapt flexibly to new environments, and
• interact with people in meaningful and reliable ways.

In the era of large-scale foundation models, we also study how these models can be efficiently adapted and personalized to individual users and specific deployment settings. Our goal is to realize intelligent visual systems that are not only scalable, but also context-aware, user-adaptive, and trustworthy in the real world.

Our research bridges and advances key areas of computer vision, deep learning, and embodied AI, with applications in autonomous driving, assistive technologies, intelligent robotics, and next-generation AI interfaces.

If you’re passionate about pushing the boundaries of vision research and building human-centered AI systems for the real world, feel free to reach out to the PI via e-mail: hyeokjunkweon@cau.ac.kr.