Baicheng Wu
About Me
I am an M.S. student in Electrical and Computer Engineering at the University of Washington. I received my Honors B.S. in Computer Science & Engineering from The Ohio State University in December 2025, where I was advised by Wei-Lun (Harry) Chao.
My research interests lie in computer vision, with a focus on 3D vision and video understanding, particularly learning robust representations from motion, geometry, and large-scale visual data.
Research Interests
- 3D vision and stereo perception, including depth estimation and geometric reasoning
- Video understanding with an emphasis on motion-based representation learning
- Learning from large-scale visual datasets and evaluating generalization
- Interpreting how deep models rely on temporal and structural cues
Publications
- Probing Identity-Specific Motion Signatures: A Controlled Diagnostic Study
Yingtie Lei*, Baicheng Wu*, Fangxun Liu*, Colin Lee, Ziheng Zhang, Junke Yang, Zhiyuan Tao, Xuyan Huang, Shuheng Wang, William Koran, Kyle Park, Elijah H. Buckwalter, Cheng Hsuan Chiang, Tejas Naik, Daniel Yi, Wei-Lun Chao
Under review.
* indicates equal contribution
Projects
- Stereo Depth Reconstruction & Benchmarking Pipeline
- Built a large-scale, multi-condition stereo vision dataset and an end-to-end reconstruction pipeline, including rectification, disparity estimation, and depth generation
- Designed standardized benchmarking protocols to evaluate state-of-the-art stereo models under real-world sensing variability
- Enabled systematic analysis of model robustness across lighting conditions, outdoor scenes, and capture setups
News
- Sep 2026: Joined the Master of Science in Electrical and Computer Engineering program at the University of Washington.
- Dec 2025: Received my B.S. degree in Computer Science & Engineering from The Ohio State University.
- Nov 2025: Defended my undergraduate honors thesis under the supervision of Wei-Lun Chao and Mi Zhang.
- Nov 2025: Co-first-author paper under review at a major computer vision conference.
- Aug 2025: Built a large-scale stereo vision dataset and benchmarking pipeline for real-world depth estimation.
- Aug 2024: Started research with Prof. Wei-Lun (Harry) Chao.