My research lies in the intersection of 3D computer vision, computer graphics, and generative models. I am interested in developing controllable generative AI models to create photorealistic, diverse, and interactive virtual environments.

More specifically, my research contributes to generative AI by bridging 3D representations from computer graphics with 3D computer vision, and learning to exploit structures from 2D and 3D data. The representations and algorithms I developed are instrumental in the realization of real-world products, including text-to-3D generation at NVIDIA Picasso and 2D image annotation at Toronto Annotation Suite. My research has also been featured at NVIDIA GTC, including image-to-3D generation at GANVerse3D, and 3D asset harvesting at Neural DriveSim.

---

I am actively looking for motivated and talented students.

Prospective PhD students: I plan to hire several PhD students starting Fall 2025. If you have a strong interest or a particular research direction/idea that aligns with my research, please feel email me with a brief description of your background and research interest.

Current UM students: Please send me your CV, transcript, and a brief description of your background and why you are interested in his research. Prior research experience in computer vision, graphics or machine learning is a plus, but not a prerequisite. However, I do prefer students who’ve taken some of these classes, or who have strong skills in math, physics or coding.

Prospective interns/visiting students: Please send me your CV, transcript, and a brief description of your background and why you are interested in this research.