Shengqi Wang

PhD Student, Department of Automation, Tsinghua University

I specialize in dynamic light field reconstruction within the realm of 3D/4D Computer Vision. Beyond reconstruction, I am also investigating the architectures of large-scale visual models.

Selected Publications GitHub

Email: shengqi-21@mails.tsinghua.edu.cn

GitHub: https://github.com/Sheng-Qi

Location: Beijing, China

News

New workshop paper accepted to SIGGRAPH Asia 2026 Workshops: Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance.
1st place overall in the Sparse-View Track of the 2nd Volumetric Video Challenge.

Research Focus

Dynamic light field reconstruction for immersive 3D/4D experiences.
Architectures of large-scale visual models.

Selected Publications

Sparse-View 4D Gaussian Splatting via Spatiotemporal Priors and Generative Assistance.
Shengqi Wang, Zhengxian Yang, Kaiwen Tian, Yang Liu, Bowen Liu, Hua Du, Taicheng Huang, Jiamin Wu, Tao Yu. Accepted to SIGGRAPH Asia 2026 Workshops (SA Workshops ’26).

Challenge arXiv

🥇 Overall 1st Place, Sparse-View Track
Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement.
Zhengxian Yang*, Shengqi Wang*, Shi Pan*, Hongshuai Li, Haoxiang Wang, Lin Li, Guanjun Li, Zhengqi Wen, Borong Lin, Jianhua Tao, Tao Yu†. arXiv, 2026.

Project arXiv

SOTA on 5 Benchmarks
ImViD: Immersive Volumetric Videos for Enhanced VR Engagement.
Zhengxian Yang*, Shi Pan*, Shengqi Wang*, Haoxiang Wang, Li Lin, Guanjun Li, Zhengqi Wen†, Borong Lin†, Jianhua Tao†, Tao Yu†. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

Project arXiv

CVPR 2025 Highlight

* Co-first authors. † Corresponding authors.

Education

PhD Student, Department of Automation, Tsinghua University
2025 - Now
Undergraduate Student, Department of Automation, Tsinghua University
2021 - 2025