Chenghao Qian

About me

I am currently pursuing a Ph.D. at Virtuocity, and a visiting researcher at the University of Cambridge. I completed my master's degree at the University of Sydney and had industrial experience working in the fields of robotics and autonomous driving.

My works aim to bridge generative models and embodied agents to
build systems that 👁️ perceive, 🧠 reason, and 🤖 act safely in the real world.

Experience

Parallel Domain · Research Associate

XPENG Robotics · Sr. Algorithm Engineer

UBTech Robotics · Algorithm Engineer

Research Interests

3D & Video World Models
Physics-guided Generation
Inverse Modelling
Robust Perception

I am open to research collaborations. Please feel free to contact me at tscq@leeds.ac.uk.

News

[04/2026]	I gave a talk at the University of Cambridge.
[02/2026]	I’m co-organizing CVPR 2026 LoViF Workshop. Please join us！
[11/2025]	One paper got accepted by AAAI 2026!
[10/2025]	Presented our paper at IROS 2025!
[09/2025]	One paper got accepted by ICCV Workshop on Generating Digital Twins from Images and Videos.
[03/2025]	I gave a talk at the Institute for Safe Autonomy, University of York.
[03/2025]	Invited by Auto-Driving Heart to give a livestream talk.
[03/2025]	One paper accepted to IEEE RA-L.
[01/2025]	One paper got accepted by IEEE ICRA 2025.
[12/2024]	AllWeatherNet received the 🌟Overall Best Student Paper Award *(1 out of 2106)* at ICPR 2024.

Publications

2026

RoboSoft

Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception

Yuhu Guo, Zhikai Shen, Jiasheng Qu, Chenghao Qian, Yuming Huang, Bin Chen, and Guoxing Fang

2026
AAAI

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field

Chenghao Qian, Wenjing Li, Yuhu Guo, and Gustav Markkula

2026

Code

2025

ICCV-W

3D Weather Editing with 4D Gaussian Field

Chenghao Qian, Wenjing Li, Yuhu Guo, and Gustav Markkula

2025

Code
ICRA

3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting

Chenghao Qian, Yuhu Guo, Wenjing Li, and Gustav Markkula

IEEE International Conference on Robotics and Automation, 2025

Code
RA-L

LLM-assisted procedural weather generation for domain-generalized semantic segmentation

Chenghao Qian, Yuhu Guo, Yuhong Mo, and Wenjing Li

IEEE Robotics and Automation Letters, 2025

Code

2024

ICPR

🌟 Best Paper Award (1/2106): Unified Image Enhancement for Autonomous Driving Under Adverse Weather and Low-Light Conditions

Chenghao Qian, Mahdi Rezaei, Saeed Anwar, Wenjing Li, Tanveer Hussain, Mohsen Azarmi, and Wei Wang

In International Conference on Pattern Recognition, 2024

Code

Services

Reviewer

Conference/Workshop:

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Annual Conference on Neural Information Processing Systems (NeurIPS)
European Conference on Computer Vision (ECCV)
ACM SIGGRAPH Asia (SIGGRAPH Asia)
AAAI Conference on Artificial Intelligence (AAAI)
IEEE International Conference on Robotics and Automation (ICRA)
International Conference on Pattern Recognition (ICPR)
Embodied World Models for Decision Making (NeurIPS Workshop)
Generating Digital Twins from Images and Videos (ICCV Workshop)

Journal:

International Journal of Computer Vision (IJCV)
IEEE Transactions on Visualization and Computer Graphics (TVCG)

Organizer/Co-organizer

1st Workshop on Low-Level Vision Frontiers (@CVPR 2026)

Mentorship

Qiangbo Zhang, Driving Scene Simulation, University of Science and Technology of China

Yanpu Wang, 3D Scene Understanding, Hefei University of Technology

Lele Hu, Domain Generalization, Hefei University of Technology

Tutor

COMP3631 Intelligent Systems and Robotics, University of Leeds

COMP2811 User Interface, University of Leeds