Fundamental Vision’s Website
The Fundamental Vision Laboratory is leaded by Associate Professor Jifeng Dai, affiliated with Electronic Engineering, Tsinghua University. The laboratory is mainly engaged in the fields of computer vision and deep learning, dedicated to developing fundamental approaches to advance visual perception and artificial general intelligence. Currently, there are four main research directions: foundation model for visual perception, generic model for multi-modal perception, perception and decision-making integration for autonomous driving, and foundation model for general intelligent agents. The laboratory has published more than 60 academic papers. Some of the papers, represented by deformable convolution, have become benchmark methods in the field and have been integrated as standard operators in PyTorch.
Highlights
Our Research
We are interested in developing foundational algorithms, models, and tools for visual perception as well as exploring unified approaches for general vision-centric multi-modal tasks and open-world scenarios.
Our Publications
We try our best to do research with long-term impact.
Our Team
I didn’t meet you during the best times of my life; it’s meeting you that gave me the best times of my life.