Research

My research lies at the intersection of Computer Vision, Geometry, and Machine Learning, with a long-term aim of developing intelligent models that emulate the human visual system. In the short term, my research mainly focuses on data-efficient deep learning, and deep learning for 3D vision.

Computer vision explores the extraction and interpretation of concepts and knowledge from visual signals, machine learning serves as a powerful tool for knowledge extraction from data, and geometry provides a foundation for understanding the physical world and how visual signals are captured. These three fields are deeply intertwined, enabling the development of advanced models that emulate the human perception.