个人简介

李天行，讲师，硕士生导师。于日本东京大学取得博士学位，随后加入北京工业大学，从事教学科研工作。

围绕计算机图形学，开展几何三维重建、变形、动画等方面的研究。在该领域发表CCF推荐A/B类期刊/会议论文多篇，并多次受邀于国际会议发表。承担多项国家级/省部级研究项目。

围绕人工智能、三维变形体仿真方向，指导多名本/硕生参加竞赛、课题，并形成高水平SCI论文及发明专利。

课程教学

计算机图形学

主要论文论著

[1] T. Li, R. Shi, Q. Zhu, L. Zhang, T. Kanai. Spectrum-Enhanced Graph Attention Network for Garment Mesh Deformation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(8): 7153-7170.

[2] T. Li, R. Shi, T. Kanai, Q. Zhu. Frequency-Divided Learning of Fine-Grained Clothing Behavior via Flexible Dynamic Graphs[J]. IEEE Transactions on Visualization and Computer Graphics, 2025, 31(10): 9166-9178.

[3] T. Li, R. Shi, Q. Zhu, T. Kanai. SwinGar: Spectrum-Inspired Neural Dynamic Deformation for Free-Swinging Garments[J]. IEEE Transactions on Visualization and Computer Graphics, 2024, 30(10): 6913-6927. (Presented at Pacific Graphics 2024)

[4] T. Li, R. Shi, T. Kanai. MultiResGNet: Approximating Nonlinear Deformation via Multi-Resolution Graphs[J]. Computer Graphics Forum, 2021, 40(2): 537–548. (Presented at Eurographics 2021)

[5] T. Li, R. Shi, T. Kanai. Detail-Aware Deep Clothing Animations Infused with Multi-Source Attributes[J]. Computer Graphics Forum, 2023, 42(1): 231-244. (Presented at Eurographics 2023)