Portrait of Ziqi Cai

Ziqi Cai (蔡子祺)

Ph.D. Student · School of Computer Science, Peking University

About

Hi! I'm a second-year Ph.D. student at the Camera Intelligence Lab, Peking University, advised by Prof. Boxin Shi. My research focuses on 3D vision, physically grounded visual generation, and generative models — with a particular interest in bringing the physics of light into how models perceive and create images and video. Before Peking University, I received my bachelor's degree from Beijing Jiaotong University and interned at the Institute of Computing Technology, Chinese Academy of Sciences, where I was fortunate to work with Prof. Lin Gao, Prof. Hongbo Fu, Prof. Yu-Kun Lai, Shu-Yu Chen, and Kaiwen Jiang. I'm also grateful to have received the President's Scholarship at Peking University.

Publications

Teaser for Video Generation Models Are Inherent Lighting Estimators
ECCV 2026
Video Generation Models Are Inherent Lighting Estimators
Ziqi Cai, Shuchen Weng, Kaiqi Liu, Zifeng Wang, Zhiquan Zhang, Minggui Teng, Han Jiang, Boxin Shi
European Conference on Computer Vision (ECCV), 2026
@InProceedings{Cai_2026_ECCV_Lighting,
  author    = {Cai, Ziqi and Weng, Shuchen and Liu, Kaiqi and Wang, Zifeng and Zhang, Zhiquan and Teng, Minggui and Jiang, Han and Shi, Boxin},
  title     = {Video Generation Models Are Inherent Lighting Estimators},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2026},
}
Teaser for Lighting-grounded Video Generation with Renderer-based Agent Reasoning
CVPR 2026
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
Ziqi Cai, Taoyu Yang, Zheng Chang, Si Li, Han Jiang, Shuchen Weng, Boxin Shi
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
@InProceedings{Cai_2026_CVPR,
  author    = {Cai, Ziqi and Yang, Taoyu and Chang, Zheng and Li, Si and Jiang, Han and Weng, Shuchen and Shi, Boxin},
  title     = {Lighting-grounded Video Generation with Renderer-based Agent Reasoning},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2026},
}
Teaser for MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
ECCV 2026
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
Kaiqi Liu, Yunyao Mao, Ziqi Cai, Zheng Geng, Jing Wang, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Shuchen Weng, Boxin Shi
European Conference on Computer Vision (ECCV), 2026
@InProceedings{Liu_2026_ECCV_MAVIN,
  author    = {Liu, Kaiqi and Mao, Yunyao and Cai, Ziqi and Geng, Zheng and Wang, Jing and Wang, Qiulin and Wang, Xintao and Wan, Pengfei and Gai, Kun and Weng, Shuchen and Shi, Boxin},
  title     = {MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2026},
}
Teaser for ReContraster
ACL 2026
ReContraster: Making Your Posters Stand Out with Regional Contrast
Peixuan Zhang, Zijian Jia, Ziqi Cai, Shuchen Weng, Si Li, Boxin Shi
Annual Meeting of the Association for Computational Linguistics (ACL), 2026
@InProceedings{Zhang_2026_ACL,
  author    = {Zhang, Peixuan and Jia, Zijian and Cai, Ziqi and Weng, Shuchen and Li, Si and Shi, Boxin},
  title     = {ReContraster: Making your posters stand out with regional contrast},
  booktitle = {Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL)},
  year      = {2026},
}
Teaser for PhyS-EdiT
CVPR 2025
PhyS-EdiT: Physics-aware Semantic Image Editing with Text Description
Ziqi Cai, Shuchen Weng, Yifei Xia, Boxin Shi
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
@InProceedings{Cai_2025_CVPR,
  author    = {Cai, Ziqi and Weng, Shuchen and Xia, Yifei and Shi, Boxin},
  title     = {PhyS-EdiT: Physics-aware semantic image editing with text description},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2025},
}
Teaser for Unified Reconstruction of Static and Dynamic Scenes from Events
CVPR 2025Highlight
Unified Reconstruction of Static and Dynamic Scenes from Events
Qiyao Gao, Peiqi Duan, Hanyue Lou, Minggui Teng, Ziqi Cai, Xu Chen, Boxin Shi
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
@InProceedings{Gao2025Unified,
  author    = {Qiyao Gao and Peiqi Duan and Hanyue Lou and Minggui Teng and Ziqi Cai and Xu Chen and Boxin Shi},
  title     = {Unified Reconstruction of Static and Dynamic Scenes from Events},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2025},
}
Teaser for Real-time 3D-aware Portrait Video Relighting
CVPR 2024Highlight
Real-time 3D-aware Portrait Video Relighting
Ziqi Cai, Kaiwen Jiang, Shu-Yu Chen, Yu-Kun Lai, Hongbo Fu, Boxin Shi, Lin Gao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
@InProceedings{Cai_2024_CVPR,
  author    = {Cai, Ziqi and Jiang, Kaiwen and Chen, Shu-Yu and Lai, Yu-Kun and Fu, Hongbo and Shi, Boxin and Gao, Lin},
  title     = {Real-time 3{D}-aware Portrait Video Relighting},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2024},
  pages     = {6221-6231},
}
Pipeline for DreamPolish
arXiv 2024
DreamPolish: Domain Score Distillation with Progressive Geometry Generation
Yean Cheng*, Ziqi Cai*, Ming Ding, Wendi Zheng, Shiyu Huang, Yuxiao Dong, Jie Tang, Boxin Shi
arXiv:2411.01602
@misc{cheng2024dreampolish,
  title         = {Dream{P}olish: Domain Score Distillation With Progressive Geometry Generation},
  author        = {Yean Cheng and Ziqi Cai and Ming Ding and Wendi Zheng and Shiyu Huang and Yuxiao Dong and Jie Tang and Boxin Shi},
  year          = {2024},
  eprint        = {2411.01602},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2411.01602},
}