姓名：徐群策

职称：助理研究员

邮箱：quncexu@tsinghua.edu.cn

教育背景

工学学士 (计算机科学与技术), 兰州大学, 中国, 2016;

工学博士 (计算机科学与技术), 巴斯大学, 英国, 2021.

研究领域

计算机图形学；几何计算；人工智能

研究概况

主要从事计算机图形学，特别专注于三维几何重建。在三维几何数据处理与建模方面，提出了基于通用度量的点云去噪与基于各向异性的表面网格质量优化方法；在三维内容编辑方面，提出了一种基于高斯泼溅的分割算法和工具；在动态三维重建方面，提出了一种基于稀疏神经辐射场的高效建模方法；在碎片重组的三维重建方面，提出了一种基于扩散模型的深度学习碎片重组算法等。

学术成果

[1] Qun-Ce Xu, Bailin Deng, Yong-Liang Yang. Ellipsoid Packing Structures on Freeform Surfaces. Computer Graphics Forum 2018, 37(7): 87-95.

[2] Qun-Ce Xu, Dong-Ming Yan, Wenbin Li, Yong-Liang Yang. Anisotropic Surface Remeshing without Obtuse Angles. Computer Graphics Forum 2019, 38(7): 755-763.

[3] Yassir Saquil, Qun-Ce Xu, Yong-Liang Yang, Peter Hall. Rank3DGAN: Semantic Mesh Generation Using Relative Attributes. AAAI 2020: 5586-5594.

[4] Qun-Ce Xu, Tai-Jiang Mu, Yong-Liang Yang: A survey of deep learning-based 3D shape generation. Comput. Vis. Media 9(3): 407-442 (2023).

[5] Qun-Ce Xu, Yong-Liang Yang, Bailin Deng: Point cloud denoising using a generalized error metric. Graph. Model. 133: 101216 (2024).

[6] Mingyuan Shen, Qun-Ce Xu, Tai-Jiang Mu: Disentangling Head NeRF for 3D Facial Animation. Computational Visual Media Conference 2024.

[7] Qi-Yuan Feng, Hao-Xiang Chen, Qun-Ce Xu (Corresponding author), Tai-Jiang Mu: SLS4D: Sparse Latent Space for 4D Novel View Synthesis. IEEE Transactions on Visualization and Computer Graphics DOI: 10.1109/TVCG.2024.3429421 Page(s): 1–14.

[8] Qun-Ce Xu, Hao-Xiang Chen, Jiacheng Hua, Xiaohua Zhan, Yongliang Yang, Tai-Jiang Mu: FragmentDiff: A Diffusion Model for Fractured Object Assembly. In SIGGRAPH Asia 2024 Conference Papers (pp. 1-12).

[9] Qi-Yuan Feng, Geng-Chen Cao, Hao-Xiang Chen, Qun-Ce Xu (Corresponding author), Tai-Jiang Mu, Ralph Martin, Shi-Min Hu: EVSplitting: An Efficient and Visually Consistent Splitting Algorithm for 3D Gaussian Splatting. In SIGGRAPH Asia 2024 Conference Papers (pp. 1-11).

[10] Qun-Ce Xu, Yan-Pei Cao, Weihao Cheng, Tai-Jiang Mu, Ying Shan, Yongliang Yang, Shi-Min Hu: High-accuracy Fractured Object Reassembly under Arbitrary Poses. Computational Visual Media Conference 2025 (Accepted).