HOME NEWS PUBLICATIONS TEACHING AWARDS
boy

Zhenwei (Zavier) Wang

Email: zwwang96 [at] gmail.com

Github  /  LinkedIn

I am a fourth-year Ph.D. student at the Department of Computer Science, City University of Hong Kong under the supervision of Prof. Rynson W.H. Lau. I am also a visiting scholar at VCG@Harvard University advised by Prof. Hanspeter Pfister. During my Ph.D. study, I was fortunate to work with Tengfei Wang and Ziwei Liu from Shanghai AI Lab and MMLab@NTU. I was also lucky to closely collaborate with Nanxuan Zhao from Adobe Research. I received my B.Eng. degree from Xiamen University.

My research interest lies in the areas of computer graphics, computer vision, and human-computer interaction. Recently, I am working on AI-based visual content generation and manipulation, such as:

  • 3D generative modeling, such as personalized 3D asset generation, multi-view diffusion, sparse-view 3D reconstruction, etc.
  • Image editing & generation with minimal annotated data, especially in the context of data-driven graphic design

    • News

    I am actively seeking job/intern opportunities for Summer or Fall 2025. Feel free to reach out to me!

  • [Apr. 2024] One paper accepted to SIGGRAPH 2024. See you in Denver!
  • [Dec. 2023] One paper accepted to AAAI 2024.
  • [Apr. 2023] One paper accepted to SIGGRAPH 2023 (journal track).

    • Selected Publications

    (*equal contribution)

    		Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
    Zhenwei Wang*, Tengfei Wang*, Zexin He, Gerhard Hancke, Ziwei Liu Rynson W.H. Lau,
    preprint, 2024
    arXiv / project page / code / video

    A 3D diffusion model with RAG, supporting 3D generation from text, image, and existing 3D models.

    		ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
    Zhenwei Wang, Tengfei Wang, Gerhard Hancke, Ziwei Liu Rynson W.H. Lau,
    Proc. ACM SIGGRAPH, Aug. 2024
    arXiv / project page / code / video

    Generate a gallery of 3D assets with consistent themes from a few exemplars.

    		Recasting Regional Lighting for Shadow Removal
    Yuhao Liu, Zhanghan ke, Ke Xu, Fang Liu, Zhenwei Wang, Rynson W.H. Lau,
    AAAI, Feb. 2024
    arXiv / project page

    Shadow removal approach that corrects degraded textures in shadow regions conditioned on recovered illumination.

    		Language-based Photo Color Adjustment for Graphic Designs
    Zhenwei Wang*, Nanxuan Zhao*, Gerhard Hancke, Rynson W.H. Lau,
    ACM Trans. on Graphics (Proc. ACM SIGGRAPH 2023), Aug. 2023
    arXiv / project page / video

    Present LangRecol, a novel language-based approach for recoloring photos in graphic designs.

    Teaching Assistant

  • Virtual Reality Technologies and Applications (CS4188/CS5188)
  • Information Security for eCommerce (CS5285)
  • Internet Security and e-Commerce Protocols (CS4286)

    • Selected Awards

  • Outstanding Academic Performance Award, City University of Hong Kong, 2023, 2024
  • Outstanding Graduate, Xiamen University, 2020
  • Outstanding Student, Xiamen University, 2019, 2020
  • Huang Xilie Scholarship, Xiamen University (Top 2%), 2019, 2020
  • First-Class Scholarship (Top 3%), 2018

    • Experience and Collaborations