
Ph.D. student Wenyan Cong and others won the Best Paper Award at the AI for Content Creation (AI4CC) Workshop, held at the Computer Vision and Pattern Recognition Conference 2025 (CVPR), one of the top conferences in computer vision. The award was for her work on “VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment.”
The paper was co-authored by Hanqing Zhu (UT Austin), Kevin Wang (UT Austin), Jiahui Lei (UPenn), Colton Stearns (Stanford University), Yuanhao Cai (Johns Hopkins University), Dilin Wang (Meta), Rakesh Ranjan (Meta), Matt Feiszli (Meta), Leonidas Guibas (Stanford University), with co-advising from Professor Zhangyang "Atlas" Wang (UT Austin), Weiyao Wang (Meta), and Zhiwen Fan (UT Austin).
The paper introduces VideoLifter, an efficient framework for lifting long videos into 3D scenes. It addresses the scalability and consistency challenges inherent in long video sequences while achieving over 5× speedup compared to state-of-the-art methods—making high-quality 3D reconstruction both accurate and practical at scale.
The AI4CC Workshop at CVPR is a leading venue for research at the intersection of AI and content creation, including advances in video synthesis, 3D reconstruction, and generative modeling.
Wenyan Cong received her Bachelor’s and Master’s degrees in Computer Science from Shanghai Jiao Tong University and joined Texas ECE in Fall 2022. She is advised by Prof. Atlas Wang.