Zhengwentai Sun
Scholar

Zhengwentai Sun

Google Scholar ID: S47VWNoAAAAJ
The Chinese University of Hong Kong, Shenzhen
Computer VisionGANDiffusion Models
Citations & Impact
All-time
Citations
157
 
H-index
4
 
i10-index
4
 
Publications
12
 
Co-authors
1
list available
Resume (English only)
Academic Achievements
  • 1. He, H., Sun, Z., Fan, J., & Mok, P. Y. (2025). TiPGAN: High-quality tileable textures synthesis with intrinsic priors for cloth digitization applications. Computer-Aided Design.
  • 2. Sun, Z., Zhou, Y., & Mok, P. Y. (2025). CoDE-GAN: Content Decoupled and Enhanced GAN for Sketch-guided Flexible Fashion Editing. ToMM.
  • 3. Pan, S., Sun, Z., Wang, C., Zhang, J. (2024). A 3D Virtual Try-on Method with Global-Local Alignment and Diffusion Model. IEEE ICASSP 2024.
  • 4. Sun, Z., Zhou, Y., He, H., & Mok, P. Y. (2023). SGDiff: A Style-Guided Diffusion Model for Fashion Synthesis. ACM Multimedia 2023.
  • 5. Lei, W., Mei, H., Sun, Z., Ye, S., Gu, R., Wang, H., ... & Wang, G. (2021). Automatic segmentation of organs-at-risk from head-and-neck CT using separable convolutional neural network with hard-region-weighted loss. Neurocomputing, 442, 184-199.
  • 6. Mei, H., Lei, W., Gu, R., Ye, S., Sun, Z., Zhang, S., & Wang, G. (2021). Automatic segmentation of gross target volume of nasopharynx cancer using ensemble of multiscale deep neural networks with spatial attention. Neurocomputing, 438, 211-222.
Research Experience
  • 1. Teaching Assistant for CSC1006 - Artificial Intelligence for Science and Engineering, 2025
  • 2. Teaching Assistant for ITC446XE - Mobile App Design for Fashion, 2023
  • 3. Intern at Tencent LightSpeed Studio, 2021
Education
  • 1. Ph.D. student at The Chinese University of Hong Kong, Shenzhen, supervised by Prof. Xiaoguang Han
  • 2. MPhil degree at The Hong Kong Polytechnic University, supervised by Prof. Tracy Mok
  • 3. Bachelor's degree from the University of Electronic Science and Technology of China
Background
  • Research interests include generative models such as GANs and diffusion models, particularly their applications in human-centric tasks. Additionally, exploring Large Language Models (LLMs) and their interaction with human users and generative vision models.
Miscellany
  • Open Source Project: Life-Reload Simulator is an innovative life simulation game powered by GPT-3.5-turbo, offering a unique experience with its dynamic content generation and immersive gameplay.
Co-authors
1 total