Zhiqi Li (李治琦)

myself.jpg

I am a Ph.D. student in the School of Engineering at Westlake University, jointly with Zhejiang University (ZJU), under the supervision of Prof. Peidong Liu. Prior to this, I earned my Bachelor’s degree from Shanghai JiaoTong University (SJTU) in 2022.

My research interests center on core applications within the field of 3D vision, including 3D Content Generation, Feedforward 3D Reconstruction, World Models. I am particularly passionate about developing efficient and scalable algorithms that bridge the gap between digital representation and real-world understanding, with the aim of enabling more intelligent and interactive 3D systems.

I am always eager to exchange ideas and explore potential collaborations. Please feel free to reach out if you are interested in my work or have related research topics to discuss.

[CV]

news

Jun 18, 2026 Our paper NeuWorld is accepted by ECCV 2026! :sparkles: :smile:
Feb 26, 2025 Our paper Omni-Scene is accepted by CVPR 2025! :sparkles: :smile:
Nov 02, 2024 Our paper MVControl is accepted by 3DV 2025! :sparkles: :smile:

Publications

  1. ECCV 2026
    teaser_neuworld.png
    Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
    Zhiqi Li, Chengrui Dong, Zhenhua Du, Hangning Zhou, Cong Qiu, Hailong Qin, and 3 more authors
    In European Conference on Computer Vision (ECCV), 2026
    arXiv Code Website
  2. ArXiv 2025
    teaser_moca.png
    MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
    Zhiqi Li, Wenhuan Li, Tengfei Wang†, Zhenwei Wang, Junta Wu, Haoyuan Wang, and 5 more authors
    arXiv preprint arXiv:2512.07628, 2025
    arXiv Code Website
  3. ArXiv 2025
    teaser_quadgpt.jpg
    QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
    Jian Liu, Chunshi Wang, Song Guo, Haohan Weng, Zhen Zhou, Zhiqi Li, and 5 more authors
    arXiv preprint arXiv:2509.21420, 2025
    arXiv Website
  4. ArXiv 2025
    teaser_vicasplat.jpg
    VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames
    Zhiqi Li, Chengrui Dong, Yiming Chen, Zhangchi Huang, and Peidong Liu†
    arXiv preprint arXiv:2503.10286, 2025
    arXiv Code Website
  5. CVPR 2025
    teaser_omniscene.png
    Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
    Dongxu Wei, Zhiqi Li, and Peidong Liu†
    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025
    arXiv Code Website
  6. 3DV 2025
    teaser_mvcontrol.jpg
    Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting
    Zhiqi Li, Yiming Chen, Lingzhe Zhao, and Peidong Liu†
    In 2025 International Conference on 3D Vision (3DV), 2025
    arXiv Code Website
  7. NeurIPS 2024
    teaser_dreammesh4d.gif
    DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
    Zhiqi Li*, Yiming Chen*, and Peidong Liu†
    Advances in Neural Information Processing Systems, 2024
    arXiv Code Website

Experiences

Apr. 2026 - Jun. 2026 Research Intern, ByteDance Soaring Star Talent Program, Hangzhou. Work on digital human video generation.
Apr. 2025 - Nov. 2025 Research Intern, Tencent Hunyuan, Shenzhen. Work on compositional 3D generation.

Services

Conference Reviewer ICLR, NeurIPS, 3DV.