Qihang ZHANG

qihang_thai3.png

Qihang Zhang is a final-year Ph.D. student at Multimedia Lab (MMLab), The Chinese University of Hong Kong, advised by Bolei Zhou and Dahua Lin. He is currently a visiting student at Stanford advised by Gordon Wetzstein.

His research interests focus on generative models, particularly in the 3D and video domains. He has been fortunate to gain extensive industry experience, including research internship at Apple MLR, Snap Research, Shanghai AI Lab, and SenseTime Research.

I will graduate in 2025’s summer. Feel free to reach out if you have suitable openings.


News

Jan 22, 2025 3DitScene (3D-aware image editing) and DART (diffusion + auto regressive model) are accepted to ICLR 25.
May 13, 2024 I start my intern at Apple! See you in New York City. 🗽
Feb 27, 2024 Two papers (BerfScene, SceneWiz3D) focused on 3D scene generation are accepted to CVPR24.
Sep 30, 2023 One paper on GAN’s architecture is accepted to NeurIPS23.
Jun 30, 2023 One paper on 3D-aware pretraining is accepted to ICCV23.
Jun 18, 2023 I start my intern at Snap Inc.! See you in Los Angeles.🌴
Jan 21, 2023 Our paper on video generation (StyleSV) is accepted to ICLR 23. 🎞
Jul 5, 2022 Our paper on policy pretraining and visuomotor policy learning (ACO) is accepted to ECCV 22. 🛣

Selected Publications

  1. Preprint
    World-consistent Video Diffusion with Explicit 3D Modeling
    Qihang Zhang, Shuangfei Zhai, Miguel Angel Bautista Martin, Kevin Miao, Alexander Toshev, Josh Susskind, and Jiatao Gu
    Preprint (Preprint) , 2024
    PDF Website
  2. Preprint
    DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models
    Kevin Miao, Harsh Agrawal, Qihang Zhang, Federico Semeraro, Marco Cavallo, Jiatao Gu, and Alexander Toshev
    Preprint (Preprint) , 2024
    PDF
  3. ICLR
    Dart: Denoising autoregressive transformer for scalable text-to-image generation
    Jiatao Gu, Yuyang Wang, Yizhe Zhang, Qihang Zhang, Dinghuai Zhang, Navdeep Jaitly, Josh Susskind, and Shuangfei Zhai
    International Conference on Learning Representations (ICLR) , 2025
    PDF
  4. ICLR
    3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
    Qihang Zhang, Yinghao Xu, Chaoyang Wang, Hsin-Ying Lee, Gordon Wetzstein, Bolei Zhou, and Ceyuan Yang
    International Conference on Learning Representations (ICLR) , 2025
    PDF Code Website
  5. CVPR
    SceneWiz3D: Towards Text-guided 3D Scene Composition
    Qihang Zhang, Chaoyang Wang, Aliaksandr Siarohin, Peiye Zhuang, Yinghao Xu, Ceyuan Yang, Dahua Lin, Bolei Zhou, Sergey Tulyakov, and Hsin-Ying Lee
    Computer Vision and Pattern Recognition (CVPR) , 2024
    PDF Code Website
  6. CVPR
    BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation
    Qihang Zhang, Yinghao Xu, Yujun Shen, Bo Dai, Bolei Zhou, and Ceyuan Yang
    Computer Vision and Pattern Recognition (CVPR) , 2024
    PDF Code Website
  7. NeurIPS
    Learning Modulated Transformation in GANs
    Ceyuan Yang, Qihang Zhang, Yinghao Xu, Jiapeng Zhu, Yujun Shen, and Bo Dai
    Neural Information Processing Systems (NeurIPS) , 2023
    PDF Code
  8. ICLR
    Towards Smooth Video Composition
    Qihang Zhang, Ceyuan Yang, Yujun Shen, Yinghao Xu, and Bolei Zhou
    International Conference on Learning Representations (ICLR) , 2023
    PDF Code Website
  9. ECCV
    Learn to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
    Qihang Zhang, Zhenghao Peng, and Bolei Zhou
    European Conference on Computer Vision (ECCV) , 2022
    PDF Code Video Website
  10. TPAMI
    MetaDrive: Composing Diverse Driving Scenarios for Generalizable Learning
    Quanyi Li*, Zhenghao Peng*, Lan Feng, Qihang Zhang, Zhenghai Xue, and Bolei Zhou
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2022
    PDF Code Video Website
  11. IEEE TIP
    F^3A-GAN: Facial Flow for Face Animation With Generative Adversarial Networks
    Xintian Wu, Qihang Zhang, Yiming Wu, Huanyu Wang, Songyuan Li, Lingyun Sun, and Xi Li
    IEEE Transactions on Image Processing (IEEE TIP) , 2021
    PDF


Experiences

Stanford
Visiting Research Scholar, Stanford Computational Imaging Lab
Jan. 2025 - June. 2025
Apple
Research Intern, Machine Learning Research, Apple
May. 2024 - Oct. 2024
Host by Jiatao Gu.
Snap
Research Intern, Creative Vision Group, Snap Research
June. 2023 - Oct. 2023
Shanghai AI Laboratory
Research Intern, Shanghai Artificial Intelligence Laboratory
Sept. 2022 - May. 2023
Host by Ceyuan Yang.
公司2图标
Research Intern, Sensetime Inc
Aug. 2020 - May. 2021
Host by Chunxiao Liu.