Zhuoman Liu (刘卓蔓)

Google Scholar. GitHub. Email: zhuo-man.liu@connect.polyu.hk

avatar.jpg

I am currently a Ph.D. candidate at The Hong Kong Polytechnic University (PolyU), supervised by Prof. Yan Luximon (AEDLAB). My research interests include 3D reconstruction, neural rendering, mesh deformation, and parametric modeling.

I received my bachelor’s degree in Software Engineering from South China University of Technology (SCUT). Following that, I have worked as a Research Associate in the Robot Perception group at CVTE Research, and completed an internship at SenseTime’s International R&D Center (IRDC). I have publications on generative models, novel view synthesis, and mesh deformation. My works on detection and segmentation have been effectively deployed on commercial products.

---- Finding internship/visiting positions!

News

Feb 27, 2025 Two papers were accepted by CVPR! One on 4D dynamic physical scene simulation and one on Gaussian talking-head generation.
Jan 10, 2025 Our DDF-ISM on CT-based mesh deformation was accepted at TVCG.
Sep 22, 2023 Our RayDF on neural representation for 3D reconstruction was accepted at NeurIPS.
Feb 28, 2023 Our SDT on handwriting generation was accepted at CVPR. 🔥The code is trending with 1k+ stars!
Jan 28, 2021 Our SCGN on generative novel view synthesis was published at TMM.

Selected Publications

  1. physflow.gif
    Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation
    Zhuoman Liu, Weicai Ye, Yan Luximon, Pengfei Wan, and Di Zhang
    CVPR, 2025
  2. mggtalk.png
    Monocular and Generalizable Gaussian Talking Head Animation
    Shengjie Gong, Haojie Li, Jiapeng Tang, Dongming Hu, Shuangping Huang, Hao Chen, Tianshui Chen, and Zhuoman Liu
    CVPR, 2025
  3. ddfism.jpg
    DDF-ISM: Internal Structure Modeling of Human Head Using Probabilistic Directed Distance Field
    Zhuoman Liu, Yan Luximon, Wei Lin Ng, and Eric Chung
    TVCG, 2025
  4. raydf.gif
    RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency
    Zhuoman Liu, Bo Yang, Yan Luximon, Ajay Kumar, and Jinxi Li
    NeurIPS, 2023
  5. sdt.png
    Disentangling Writer and Character Styles for Handwriting Generation
    Gang Dai, Yifan Zhang, Qingfeng Wang, Qing Du, Zhuliang Yu, Zhuoman Liu, and Shuangping Huang
    CVPR, 2023
  6. scgn.jpg
    Deep View Synthesis via Self-Consistent Generative Network
    Zhuoman Liu, Wei Jia, Ming Yang, Peiyao Luo, Yong Guo, and Mingkui Tan
    TMM, 2021