I am a Ph.D. candidate in Elmore Family School of Electrical and Computer Engineering at Purdue University and working with Prof. Qi Guo. My current research focuses on computer vision and deep learning, with a particular emphasis on the joint development of novel deep learning algorithms and camera setups to optimize overall system performance across multiple tasks, such as boundary detection and depth estimation, in photon-limited environments.

Prior to Purdue, I completed my M.S. in Khoury College of Computer Sciences at Northeastern University under the supervision of Prof. Lawson L.S. Wong. Previously, I received my B.Eng. and M.S. in Department of Process Equipment and Control Engineering at Tianjin University, advised by Prof. Liyan Liu.

Download my curriculum vitae (temporarily unavailable).

News

Education

Publications

A complete list of my publications is available on Google Scholar.

CVPR 2025

Blurry-Edges cover

Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
Wei Xu, Charles James Wagner, Junjie Luo, Qi Guo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Project page] [arXiv] [Code] [YouTube]

MMSP 2024

CT-Bound cover

CT-Bound: Robust Boundary Detection from Noisy Images Via Hybrid Convolution and Transformer Neural Networks
Wei Xu, Junjie Luo, Qi Guo
IEEE 26th International Workshop on Multimedia Signal Processing (MMSP), 2024
[arXiv] [Code]

Services

  • Reviewer: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.