Yuxi Xiao

I am a senior undergraduate student at Wuhan University and will be starting my PhD program in the State Key Laboratory of CAD&CG at Zhejiang University in September 2023, under the supervision of Prof.Xiaowei Zhou. My research interests are in the intersections of 3D vision, graphics, and robotics, specifically in the areas of 3D/4D reconstruction and novel view synthesis.

During my undergraduate studies, I had the fortune of being a research intern at CAPTAIN, where I worked under the supervision of Prof.Nan Xue and Prof.Gui-song Xia. Prior to that, I spent a year as a research assistant at CVRS, working alongside Prof.Jian Yao.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo

I'm interested in computer vision, machine learning and Robotics. Most of my recent works are trying to reconstruct the 3D or 4D information for arbitrary objects from images. Representative papers are highlighted.

Level-S2fM: Structure from Motion on Neural Level Set of Implicit Surfaces
Yuxi Xiao, Nan Xue, Tianfu Wu, Gui-Song Xia
( indicates the corresponding author)
CVPR, 2023  
project page / arXiv

Level-S2fM is a neural incremental SfM pipeline designed on the neural field, which treats the zero-level set of the implicit surface as an informative top-down regularization to manage the reconstructed 3D points, reject the outlier of correspondences by querying SDF, adjust the estimated geometries by Neural bundle adjustment.

b3do DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion
Yuxi Xiao, Li Li, Xiaodi Li, Jian Yao
IROS, 2022

We formulate the two-view structure from motion as an MLE problem, which is solved with proposed deep iterative solver.

This website template was borrower from Jonathon Barron.