Zhendong Wang (王震东)

I am currently a 4th-year Ph.D. student at University of Science and Technology of China (USTC), supervised by Prof. Houqiang Li and Prof. Wengang Zhou . Before that, I received my Bachelor degree from Harbin Institute of Technology (HIT) in 2021. I collaborate closely with Jianmin Bao.

My current research interests are computer vision and deep learning, especially visual generative models and text2image generation. Previously, my research focus was on low-level vision and deepfake detection.

I have obtained 2,900+ citations according to Google Scholar, with the seminal work Uformer contributing 2,300+ citations, which is honored as one of the Most Influential Papers in CVPR 2022 by PaperDigest.

Two of my first-author CVPR papers (DesignDiffusion, AltFreezing) are selected as oral presentations.

I am expected to graduate in June 2026. I am open to opportunities for research scientist or engineering roles in Artificial Intelligence/Computer Vision. If you are interested in my experience, don’t hesitate to contact me.

Email  /  Google Scholar  /  Github  /  CV

profile photo

Publications (* indicates equal contribution)

DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
Zhendong Wang, Jianmin Bao, Shuyang Gu, Dong Chen, Wengang Zhou, Houqiang Li
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Oral paper (~0.7%)
[paper] [code]

SmartEraser: Remove Anything from Images using Masked-Region Guidance
Longtao Jiang*, Zhendong Wang*, Jianmin Bao*, Wengang Zhou, Dongdong Chen, Lei Shi, Dong Chen, Houqiang Li
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[paper] [code]

DIRE for Diffusion-Generated Image Detection
Zhendong Wang*, Jianmin Bao*, Wengang Zhou, Weilun Wang, Hezhen Hu, Hong Chen, Houqiang Li
International Conference on Computer Vision (ICCV), 2023
[paper] [code]

AltFreezing for More General Video Face Forgery Detection
Zhendong Wang*, Jianmin Bao*, Wengang Zhou, Weilun Wang, Houqiang Li
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Oral paper (~2.5%)
[paper] [code]

Uformer: A General U-Shaped Transformer for Image Restoration
Zhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou, Jianzhuang Liu, Houqiang Li
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
PaperDigest Most Influential Papers in CVPR 2022
[paper] [code]

Research Experience

  • [2023/07 ~ 2024/06]     Microsoft Research Asia, Vision Computing Group, Research Intern (Mentor: Jianmin Bao).
  • [2020/08 ~ 2021/07]     Noah's Ark Lab, Computer Vision Lab, Research Intern (Mentor: Jianzhuang Liu).

Awards and Honors

  • Stars of Tomorrow Internship in MSRA.
    2024
  • National Scholarship (Highest honor for postgraduates in China).
    2023
  • Outstanding graduates of HIT.
    2021
  • National Scholarship (Highest honor for undergraduates in China).
    2019
  • First prize in Chinese Mathematics Competitions.
    2019
  • Second prize in ABU Robocon Robot Competitions.
    2019

Academic Services

  • Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, AAAI, ICML, IJCAI, ACMMM, ICME.
  • Journal Reviewer: TPAMI, IJCV, TIP, TMM, TCSVT.

Modified from Ze Liu and Jon Barron.