| CARVIEW |
Yao-Chih Lee
CS Ph.D. Student at the University of Maryland
Video Synthesis and 3D Vision
I am a 4th-year Ph.D. student at the University of Maryland College Park, advised by Jia-Bin Huang. My research interests include 3D computer vision and video synthesis, particularly focusing on reconstructing real-world scenes from casual videos for synthesis and editing.
My research collaborations include recent internship at Adobe (collaborating with Zhengqi Li, Eli Shechtman, Zhoutong Zhang, Joon-Young Lee, Gabriel Huang, and Jui-Hsien Wang) and prior experiences as a student researcher at Google DeepMind (mentored by Forrester Cole, Erika Lu, Tali Dekel, and Sarah Rumbley), and an earlier internship at Adobe (working with Feng Liu, Zhoutong Zhang, Kevin Blackburn-Matzen, Simon Niklaus, and Jianming Zhang).
[New] I am highly interested in an industrial full-time research position. Please feel free to connect.
-
UMD
Ph.D. Student
Today – 2022 -
Adobe Research
Research Intern
2025, 2023 -
Google DeepMind
Student Researcher
2024 -
Academia Sinica
Research Assistant
2022 - 2020 -
National Taiwan University M.S.
2020 - 2018 -
National Chiao Tung University B.S.
2018 - 2014
Publications
Generative Video Motion Editing with 3D Point Tracks [New]
Yao-Chih Lee, Zhoutong Zhang, Jiahui Huang, Jui-Hsien Wang, Joon-Young Lee, Jia-Bin Huang, Eli Shechtman, Zhengqi Li
arXiv preprint 2025
  Project page   Paper   VideoGenerative Omnimatte: Learning to Decompose Video into Layers
Yao-Chih Lee, Erika Lu, Sarah Rumbley, Michal Geyer, Jia-Bin Huang, Tali Dekel, Forrester Cole
CVPR 2025 Highlight
  Project page   Paper   Code & Data   Video
3D Video Stabilization with Depth Estimation by CNN-based Optimization
Yao-Chih Lee, Kuan-Wei Tseng, Yu-Ta Chen, Chien-Cheng Chen, Chu-Song Chen, Yi-Ping Hung
CVPR 2021
  Project page   Paper   Code   Video   Awesome video stabilization
Text-driven Visual Synthesis with Latent Diffusion Prior
Ting-Hsuan Liao, Songwei Ge, Yiran Xu, Yao-Chih Lee, Badour AlBahar, Jia-Bin Huang
arXiv preprint 2023
  Project page   arXiv
GCVD: Globally-Consistent Video Depth and Pose Estimation with Efficiency
Yao-Chih Lee, Kuan-Wei Tseng, Guan-Sheng Chen, Chu-Song Chen
arXiv preprint 2022
  arXiv   Code
PixStabNet: Fast Deep Online Video Stabilization
Yu-Ta Chen, Kuan-Wei Tseng, Yao-Chih Lee, Chun-Yu Chen, and Yi-Ping Hung
ICIP 2021
  Paper
Part-aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
Hau Chu, Jia-Hong Lee, Yao-Chih Lee, Ching-Hsien Hsu, Jia-Da Li, and Chu-Song Chen
CVPR Workshop 2021
  Paper