Yunhan Zhao
Research Engineer
Google DeepMind
Email: yunhaz5 [at] ics [dot] uci [dot] edu
CV  / 
Github  / 
Google Scholar
|
|
About
I'm a research engineer at Google DeepMind where I work on video generative models (Veo). I completed my Ph.D. degree in Computer Science at UC Irvine, advised by Prof. Charless Fowlkes. Previously, I finished my Master degree at Johns Hopkins University working with Prof. Alan Yuille.
|
Research Interests
- My research interests are in computer vision and machine learning, especially deep learning.
- My primary interests are embodied AI (vision for robotics, perception for action), generative models, and 3D scene understanding.
|
Publications
|
|
Solving Instance Detection from an Open-World Perspective
Qianqian Shen*, Yunhan Zhao*, Nahyun Kwon, Jeeeun Kim, Yanan Li, Shu Kong
CVPR, 2025
arXiv  / 
Code
|
|
Anomaly Detection of Tabular Data Using LLMs
Aodong Li, Yunhan Zhao, Chen Qiu, Marius Kloft, Padhraic Smyth, Maja Rudolph, Stephan Mandt
IJCAI, ADFM Workshop, 2024
arXiv   
|
|
Instance Tracking in 3D Scenes from Egocentric Videos
Yunhan Zhao, Haoyu Ma, Shu Kong, Charless Fowlkes
CVPR, 2024
arXiv  / 
Code
|
|
A High-Resolution Dataset for Instance Detection with Multi-View Instance Capture
Qianqian Shen*, Yunhan Zhao*, Nahyun Kwon, Jeeeun Kim, Yanan Li, Shu Kong
NeurIPS, Datasets and Benchmarks Track, 2023
arXiv  / 
Code
|
|
GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding
Yunhan Zhao, Connelly Barnes, Yuqian Zhou, Eli Shechtman, Sohrab Amirghodsi, Charless Fowlkes
WACV, 2023
arXiv
|
|
Camera Pose Matters: Improving Depth Prediction by
Mitigating Pose Distribution Bias
Yunhan Zhao, Shu Kong, Charless Fowlkes
CVPR, 2021 (Oral Presentation)
arXiv  / 
Project Page  / 
Code
|
|
Domain Decluttering: Simplifying Images to Mitigate
Synthetic-Real Domain Shift and Improve Depth Estimation
Yunhan Zhao, Shu Kong, Daeyun Shin, Charless Fowlkes
CVPR, 2020
arXiv  / 
Project Page  / 
Code
|
|
Resisting Large Data Variations via Introspective Transformation Network
Yunhan Zhao, Ye Tian, Charless Fowlkes, Wei Shen, Alan Yuille
WACV, 2020
arXiv  / 
Project Page  / 
Code
|
Invited Talks
- Imperial College London Reading Group: Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias; Irvine, CA (Remote); Jun. 2021
|
Professional Services
|
Conference Reviewer
CVPR, ICCV, ECCV, WACV, NeurIPS
Journal Reviewer
Neurocomputing, TPAMI
Workshop and Challenge Organizer
Object Instance Detection Challenge at VPLOW, CVPR 2024
The 1st workshop on Object Instance Detection InsDet, ACCV 2024
Object Instance Detection Challenge at VPLOW, CVPR 2025
|
|