Yuqi Wu

I am a second year PhD student in the Department of Automation at Tsinghua University, advised by Prof. Jiwen Lu . In 2024, I obtained my B.Eng. in the Xinya College, Tsinghua University.

I am broadly interested in computer vision and deep learning. My current research focuses on 3D vision.

Email  /  Google Scholar  /  Github

Publications

* indicates equal contribution

StreamVGGT employs temporal causal attention and leverages cached token memory to support efficient incremental on-the-fly reconstruction, enabling interative and real-time online applications.

Point3R is an online framework for dense streaming 3D reconstruction using explicit spatial memory, which achieves competitive performance with low training costs.

EmbodiedOcc formulates an embodied 3D occupancy prediction task and employs a Gaussian-based framework to accomplish it.

Website Template