Zheng Gu   顾峥

I am currently an Assistant Professor with the Visual Computing Research Center (VCC) (led by Prof. Hui Huang) at the College of Computer Science and Software Engineering, Shenzhen University.

I received my Ph.D. degree from the Reasoning and Learning (RL) Group at College of Computer, Nanjing University in 2024, advised by Prof. Yang Gao and Prof. Jing Huo. I received my dual Ph.D. degree from Department of Computer Science, City University of Hong Kong in 2025, advised by Prof. Jing Liao. I received my B.Sc. degree from Nanjing University in 2017.

Driven by a passion for Deep Generative Models, I explore the synergy between Machine Learning, Computer Vision, and Computer Graphics. Recently, my research has focused on building controllable and transferable AIGC systems that can not only generate images, videos, 3D content, or music, but also understand and evolve through Open-World scenarios to empower human creativity.

Address: L6-811, Shenzhen University Cang Hai Campus, Shenzhen, China

Email: [email protected]

Zheng Gu

News

Publications

Cycle-Consistent Tuning for Layered Image Decomposition

Zheng Gu, Min Lu, Zhida Sun, Dani Lischinski, Daniel Cohen-Or, and Hui Huang*

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026 (Accepted to appear)

[Project Page] [Arxiv] [Code]

DA4D Teaser

DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video

Jiawei Hou, Shenghao Zhang, Can Wang, Zheng Gu, Yonggen Ling, Taiping Zeng, Xiangyang Xue, and Jingbo Zhang

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026 (Accepted to appear)

[Project Page] [Arxiv]

CoT-VTM Teaser

CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning

Xikang Guan, Zheng Gu, Jing Huo*, Tianyu Ding, and Yang Gao

Findings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025

[Project Page] [Paper]

MTV-Inpaint: Multi-Task Long Video Inpainting

Shiyuan Yang, Zheng Gu, Liang Hou, Xin Tao, Pengfei Wan, Xiaodong Chen, and Jing Liao

arxiv preprint, 2025

[Project Page] [Arxiv] [Hugging Face]

LiesGAN Teaser

Task-Aware Few-Shot Image Generation via Dynamic Local Distribution Estimation and Sampling

Zheng Gu, Wenbin Li*, Tianyu Ding, Zhengli Wang, Jing Huo, Kuihua Huang, and Yang Gao

Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024

[Paper]

Analogist Teaser

Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model

Zheng Gu, Shiyuan Yang, Jing Liao*, Jing Huo*, and Yang Gao

ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2024

[Project Page] [Paper] [Arxiv] [Code] [Data]

CariMe Teaser

CariMe: Unpaired Caricature Generation with Multiple Exaggerations

Zheng Gu, Chuanqi Dong, Jing Huo*, Wenbin Li, and Yang Gao

IEEE Transactions on Multimedia (TMM), 2021

[Paper] [Arxiv] [Code] [Data]

LoFGAN Teaser

LoFGAN: Fusing Local Representations for Few-shot Image Generation

Zheng Gu†, Wenbin Li†, Jing Huo*, Lei Wang, and Yang Gao

International Conference on Computer Vision (ICCV), 2021

[Paper] [Code] [Data]

Learning Task-aware Teaser

Learning Task-aware Local Representations for Few-shot Learning

Chuanqi Dong, Wenbin Li, Jing Huo, Zheng Gu, and Yang Gao*

International Joint Conference on Artificial Intelligence (IJCAI), 2020

[Paper] [Code]

Unsupervised Domain Attention Teaser

Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition

Wen Ji, Kelei He, Jing Huo*, Zheng Gu, and Yang Gao

European Conference on Computer Vision (ECCV), 2020

[Paper] [Code]

DeepMEF Teaser

DeepMEF: A Deep Model Ensemble Framework for Video Based Multi-modal Person Identification

Chuanqi Dong, Zheng Gu, Zhonghao Huang, Wen Ji, Jing Huo, and Yang Gao

ACM Conference on Multimedia (ACM MM), 2019

[Paper] [Code]

Honors

Teaching

Service

Experience