About Me

I am Xin Yu, currently a third-year PhD candidate at the Computer Vision and Machine Intelligence Laboratory (CVMI Lab) at the University of Hong Kong, under the supervision of Professor Xiaojuan Qi. I received my Bachelor’s degree in Mathematics and Applied Mathematics from Sun Yat-sen University.

I have published several academic papers at top-tier conferences in computer vision and graphics, such as ICCV, CVPR, ECCV, and SIGGRAPH Asia, as well as leading machine learning conferences like ICLR. My work, TEXGen, was honored with the SIGGRAPH Asia 2024 Best Paper Honorable Mention.

I have been deeply involved in early technical breakthroughs with VAST (Tripo AI), a leading 3D generation startup, and have maintained a long-term collaboration with them. I also had a rewarding internship at Adobe Research in North America during the summer of 2024, where I led innovative research on how foundational video generative models and 3D synthetic data can enhance image editing.

Currently, I am dedicated to developing universal and efficient generative architectures and paradigms for 3D, image, and video generation. If you are interested in my work and would like to explore potential collaborations or career opportunities, please feel free to reach out to me!

News

• [2025-02] Our work ObjectMover (conducted during my internship at Adobe) has been accepted by CVPR 2025.
• [2024-12] TEXGen has been selected for the Best Paper Honorable Mention Award at SIGGRAPH Asia 2024.