Zhiyuan Gao

Zhiyuan Gao

PhD Student@USC

University of Southern California

I am a PhD student in Computer Science at University of Southern California, advised by Prof. Jernej Barbic. I’ve finished my Master degree in CS@USC advised by Prof. Yue Wang and Prof. Jernej Barbic. I have also interned at Vision & Graphics Lab, where I was fortunate to work with Prof. Yajie Zhao.

Interests
  • Differentiable Simulation
  • Neural Scene Representation
  • Computer Graphics
  • 3D Computer Vision
Education

  • PhD in Computer Science, 2025-

    University of Southern California

  • M.S. in Computer Science, 2023-2025

    University of Southern California

News
  •    [2025-10] One paper is accepted to NeurIPS 2025!
  •    [2025-7] One paper is accepted to ICCV 2025!
  •    [2024-12] One paper is accepted as Oral Presentation to 3DV 2025!
  •    [2024-09] One paper is accepted to WACV 2025!

Publications

*
All Vision and Graphics Others
Geometry-aware Feature Matching for Large-Scale Structure from Motion

Geometry-aware Feature Matching for Large-Scale Structure from Motion

Gonglin Chen, Jinsen Wu, Haiwei Chen, Wenbin Teng, Zhiyuan Gao, Andrew Feng, Rongjun Qin, Yajie Zhao
3DV 2025 (Oral Presentation) , 2024-12
A novel geometry-aware feature matching approach that combines detector-based and detector-free methods to improve correspondence accuracy and density for large-scale Structure from Motion.
arXiv Cite Website
Volume Rendering of Human Hand Anatomy

Volume Rendering of Human Hand Anatomy

Jingtao Huang, Bohan Wang, Zhiyuan Gao, Mianlun Zheng, George Matcuk, Jernej Barbic
arXiv , 2024-11
We propose novel transfer functions for volumetric rendering of hand MRI data that improve visualization of complex hand anatomy while maintaining fine control over tissue appearance.
arXiv Cite
Skyeyes: Ground Roaming using Aerial View Images

Skyeyes: Ground Roaming using Aerial View Images

*Zhiyuan Gao, *Wenbin Teng, Gonglin Chen, Jinsen Wu, Ningli Xu, Rongjun Qin, Andrew Feng, Yajie Zhao
WACV 2025 , 2024-10
Skyeyes is a framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience.
arXiv Cite Website
Understanding street-level urban vibrancy via spatial-temporal Wi-Fi data analytics: Case LivingLine Shanghai

Understanding street-level urban vibrancy via spatial-temporal Wi-Fi data analytics: Case LivingLine Shanghai

Yan Zhang, Chengliang Li, Jiajie Li, Zhiyuan Gao, Tianyu Su, Can Wang, Hexin Zhang, Teng Ma, Yang Liu, Weiting Xiong, Ronan Doorley, Luis Alonso, Yongqi Lou, Kent Larson
Environment and Planning B: Urban Analytics and City Science , 2024-05
Using Wi-Fi data analytics and machine learning to quantify urban vibrancy at the street level, demonstrated through a case study of urban interventions in Shanghai while preserving user privacy.
Paper PDF Cite
Refined self-attention mechanism based real-time structural response prediction method under seismic action

Refined self-attention mechanism based real-time structural response prediction method under seismic action

Shiqiao Meng, Ying Zhou, Zhiyuan Gao
Engineering Applications of Artificial Intelligence , 2024-03
Our SeisFormer model based on self-attention mechanism for real-time structural response prediction under seismic action for large-scale structures, achieving high accuracy and efficiency even with limited training data.
Paper PDF Cite
Real‐time automatic crack detection method based on drone

Real‐time automatic crack detection method based on drone

Shiqiao Meng, Zhiyuan Gao, Ying Zhou, Bin He, Abderrahim Djerrad
Computer-Aided Civil and Infrastructure Engineering , 2023-10
A real-time drone-based crack detection method that combines lightweight and high-precision algorithms with autonomous flight control for efficient building damage assessment.
Paper PDF Cite
A three-stage deep-learning-based method for crack detection of high-resolution steel box girder image

A three-stage deep-learning-based method for crack detection of high-resolution steel box girder image

Shiqiao Meng, Zhiyuan Gao, Ying Zhou, Bin He, Qingzhao Kong
Smart Structures and Systems (Excellent Award@IPC-SHM'2020) , 2022-01
A novel three-stage deep learning method for crack detection in high-resolution steel box girder images, combining patch-based CBAM ResNet-50 for localization, Attention U-Net for edge detection, and morphological operations for refinement.
Paper Cite IPC-SHM'20

Publications

Experience

 
 
 
 
 
USC Geometry, Vision, and Learning Lab
Research Intern
USC Geometry, Vision, and Learning Lab
May 2024 – Present Los Angeles, Califronia
Research on differentiable simulation for scene reconstruction and video generation, which resulted in a paper that is currently in submission.
 
 
 
 
 
USC ICT Vision & Graphics Group
Research Intern
USC ICT Vision & Graphics Group
June 2023 – September 2024 Los Angeles, Califronia
Research on urban scence reconstruction and generation based on aerial imagery, which resulted in a WACV'25 paper and a 3DV'25 paper.
 
 
 
 
 
Shanghai Research Institute for Intelligent Autonomous Systems
Research Intern
Shanghai Research Institute for Intelligent Autonomous Systems
September 2020 – March 2022 Shanghai, China
Finished several projects related to Computer Vision Application in Civil Engineering.
 
 
 
 
 
Tongji-MIT City Science Lab
Research Intern
Tongji-MIT City Science Lab
October 2020 – October 2021 Shanghai, China
Developed pedestrian trajectory analysis and mined patterns to assess activity impacts.

Posts

All you need to know about coordinate conversions
In many situations, we need to obtain the position and rotation of a camera or an object from different software applications. However, the way these parameters are acquired can vary. The representation of position and rotation may differ; we might get a camera-to-world matrix, a world-to-camera matrix, a rotation matrix, or other forms such as quaternions or Euler angles.
Last updated on Apr 7, 2024 2 min read
See all posts

Contact