Fengrui Tian   田丰瑞

I'm an incoming 2024 Fall Ph.D. student at GRASP Lab, University of Pennsylvania, advised by Prof. René Vidal. My major research direction is 3D vision.

For now, I am a master student at the College of Artificial Intelligence of Xi'an Jiaotong University, where I work on computer vision. My master's supervisor is Prof. Shaoyi Du. I am also a research intern at Tsinghua University, where I'm very fortunate to work with Prof. Yueqi Duan and focus on novel view synthesis.

Before that, I was a research intern at CCVL group of Johns Hopkins University, advised by Prof. Alan Yuille and Angtian Wang. I was also an intern at Shanghai Artificial Intelligence Laboratory, Sensetime Research and Megvii Research. I received my B.Eng. degree from the School of Software Engineering of Xi'an Jiaotong University, supervised by Prof. Zhiqiang Tian, with the honor of Best Undergraduate Thesis (rank 1/110+).

I support Slow Science but it is really hard for me to practice it now.

Email  /  Google Scholar  /  Github  /  Full CV (updated to 2023.1.19)

We propose to leverage the power of diffusion model to train a category-level pose estimator without requiring any pose annotations.

We propose Semantic Flow that builds semantic fields of dynamic scenes from monocular videos.

We propose MonoNeRF for learning a generalizable dynamic radiance field from monocular videos. While independently using 2D local features and optical flows suffers from ambiguity along the ray direction, they provide complementary constraints to jointly learn 3D point features and scene flows.

We propose a framework for self-supervised video contrastive learning.

We propose a framework for learning radiologists' experience in medical organ segmentation.

The website template was borrowed from the source code and this page.