Currently, I am a final year Ph.D. student in Computer Science, School of Electronic and Computer Engineering, Peking University, supervised by Prof. Jian Zhang. Previously, I received my B.Eng degree of software engineering from Dalian University of Technology in 2022. My main research interests include computer vision, diffusion models, and machine learning, primarily focusing on video-related Artificial Intelligence Generated Content (AIGC). Most recently, my main research topic is multimodal video generation.

I have led several interesting projects on video editing, novel view synthesis, and low-level vision, and have complished 10 papers as the first author, with . 📢 I’m open to opportunities for research intern and please feel free to get in touch via email: szyang AT stu DOT pku DOT edu DOT cn

📜 Research Area

Video-related AIGC
Novel View Synthesis
Low-level Vision

📝 Selected Publications

Equal Contribution*, Corresponding Author†, Project Leader‡; [J] Journal, [C] Conference

	GenCompositor: Generative Video Compositing with Diffusion Transformer Shuzhou Yang, Xiaoyu Li‡, Xiaodong Cun, Guangzhi Wang, Lingen Li, Ying Shan, Jian Zhang†. International Conference on Learning Representations (ICLR) [C], 2026 arXiv \| Paper \| Project Page \| Social Media \| Code Adaptively compositing videos guided by user-specified trajectories and scales.
	4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation Shuzhou Yang, Xiaodong Cun, Xiaoyu Li‡, Yaowei Li, Jian Zhang†. International Journal of Computer Vision (IJCV) [J], 2026 arXiv \| Paper \| Project Page Generating dense multi-view videos through cascaded diffusion model.
	Neural Video Field Editing Shuzhou Yang, Chong Mou, Jiwen Yu, Yuhan Wang, Xiandong Meng, Jian Zhang†. Computational Visual Media (CVM) [J], 2025 arXiv \| Paper \| Project Page \| Social Media \| Code Editing long videos coherently via neural video fields.
	Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation Shuzhou Yang, Yu Wang, Haijie Li, Jiarui Meng, Yanmin Wu, Xiandong Meng, Jian Zhang†. Visual Intelligence (VI) [J], 2025 arXiv \| Paper \| Project Page \| Social Media \| Code Using both 2D and 3D diffusion models for image-to-3D generation with hybrid fourier score distillation.
	DiffLLE: Diffusion-based Domain Calibration for Weak Supervised Low-light Image Enhancement Shuzhou Yang, Xuanyu Zhang, Yinhuai Wang, Jiwen Yu, Yuhan Wang, Jian Zhang†. International Journal of Computer Vision (IJCV) [J], 2024 arXiv \| Paper \| Social Media Bridge the gap between real scenes and training data by diffusion model prior.
	Implicit Neural Representation for Cooperative Low-light Image Enhancement Shuzhou Yang, Moxuan Ding, Yanmin Wu, Zihan Li, Jian Zhang†. International Conference on Computer Vision (ICCV) [C], 2023 arXiv \| Paper \| Social Media \| Code Normalize images by neural representation and enhance them based on CLIP prior.
	Multi-scale Synergism Ensemble Progressive and Contrastive Investigation for Image Restoration Shuzhou Yang, Zhiying Jiang, Jinyuan Liu, Xin Fan, Risheng Liu†. IEEE Transactions on Instrumentation and Measurement (TIM) [J], 2023 Paper \| Code Restore image degradation through a multi-scale progressive network.
	NeRFocus: Neural Radiance Field for 3D Synthetic Defocus Yinhuai Wang, Shuzhou Yang*, Yujie Hu, Jian Zhang†. Computer Vision and Pattern Recognition Workshop (CVPRW)* [C], 2023 arXiv \| Code Realize defocusing effect in 3D scenarios.

👔 Experience

Hunyuan, Shenzhen, China
- Mar’2026 - Present
- Research Intern in Foundation Models
- Mentors: Lucas Wang & smurfsguo
ARC Lab, Shenzhen, China
- Dec’2024 - Feb’2026
- Research Intern in Video Editing and Generation
- Mentors: Dr. Xiaoyu Li & Prof. Xiaodong Cun
AI Lab, Shenzhen, China
- Apr’2024 - Nov’2024
- Research Intern in Novel View Video Generation
- Mentor: Prof. Xiaodong Cun

💻 Academic Services

Journal Reviewer:
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- ACM Transactions on Graphics (TOG)
- International Journal of Computer Vision (IJCV)
- IEEE Transactions on Image Processing (TIP)
- IEEE Transactions on Multimedia (TMM)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)
- IEEE Journal of Selected Topics in Signal Processing (JSTSP)
Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, Siggraph, AAAI, ACM MM, etc.
Teaching assistant for computer vision course at School of Electronic and Computer Engineering, Peking University, 2023.

🏆️ Selected Honors

[2026] The Second-order Scholarship at Peking University.
[2025] Peking University May Fourth Scholarship. 🎖️
[2023] The Third-order Scholarship at Peking University.
[2023-2026] Outstanding Student Award at Peking University.
[2019-2021] The First-order Excellent Scholarship at Dalian University of Technology.

🎓 Educations

Sep’2022 - Jul’2027: Ph.D. (Computer Science), Peking University
Sep’2018 - Jul’2022: B.Eng (Software Engineering), Dalian University of Technology

	GenCompositor: Generative Video Compositing with Diffusion Transformer Shuzhou Yang, Xiaoyu Li‡, Xiaodong Cun, Guangzhi Wang, Lingen Li, Ying Shan, Jian Zhang†. International Conference on Learning Representations (ICLR) [C], 2026 arXiv \| Paper \| Project Page \| Social Media \| Code Adaptively compositing videos guided by user-specified trajectories and scales.
	4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation Shuzhou Yang, Xiaodong Cun, Xiaoyu Li‡, Yaowei Li, Jian Zhang†. International Journal of Computer Vision (IJCV) [J], 2026 arXiv \| Paper \| Project Page Generating dense multi-view videos through cascaded diffusion model.
	Neural Video Field Editing Shuzhou Yang, Chong Mou, Jiwen Yu, Yuhan Wang, Xiandong Meng, Jian Zhang†. Computational Visual Media (CVM) [J], 2025 arXiv \| Paper \| Project Page \| Social Media \| Code Editing long videos coherently via neural video fields.
	Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation Shuzhou Yang, Yu Wang, Haijie Li, Jiarui Meng, Yanmin Wu, Xiandong Meng, Jian Zhang†. Visual Intelligence (VI) [J], 2025 arXiv \| Paper \| Project Page \| Social Media \| Code Using both 2D and 3D diffusion models for image-to-3D generation with hybrid fourier score distillation.
	DiffLLE: Diffusion-based Domain Calibration for Weak Supervised Low-light Image Enhancement Shuzhou Yang, Xuanyu Zhang, Yinhuai Wang, Jiwen Yu, Yuhan Wang, Jian Zhang†. International Journal of Computer Vision (IJCV) [J], 2024 arXiv \| Paper \| Social Media Bridge the gap between real scenes and training data by diffusion model prior.
	Implicit Neural Representation for Cooperative Low-light Image Enhancement Shuzhou Yang, Moxuan Ding, Yanmin Wu, Zihan Li, Jian Zhang†. International Conference on Computer Vision (ICCV) [C], 2023 arXiv \| Paper \| Social Media \| Code Normalize images by neural representation and enhance them based on CLIP prior.
	Multi-scale Synergism Ensemble Progressive and Contrastive Investigation for Image Restoration Shuzhou Yang, Zhiying Jiang, Jinyuan Liu, Xin Fan, Risheng Liu†. IEEE Transactions on Instrumentation and Measurement (TIM) [J], 2023 Paper \| Code Restore image degradation through a multi-scale progressive network.
	NeRFocus: Neural Radiance Field for 3D Synthetic Defocus Yinhuai Wang, Shuzhou Yang*, Yujie Hu, Jian Zhang†. Computer Vision and Pattern Recognition Workshop (CVPRW)* [C], 2023 arXiv \| Code Realize defocusing effect in 3D scenarios.