who we are

Tencent Games AI Research Center (TGAIRC) is an AI research and application institute under Common R&D and Operation System (CROS) in Tencent Games. Our mission is to improve game development efficiency and quality based on AI methods and other new technologies.

Research field

Current interests

Our current interests includes AI applications in intelligent agent control, digital content creation and simulation. Based on these brand new data driven methods, game developers can build realistic world at large scale, create vivid character with life-like interaction and increase their current pipeline's efficiency.


Our AI based applications can be found in multiple games such as QQ speed mobile, Happy Poker, PUBG Mobile and so on. Working together with other teams in CROS such as game engine and motion capture studio, we can help game developer by providing cutting-edge technologies and toolkits. Let's bring the future into the present and make it real!



3d human pose estimation using spatio-temporal networks with explicit occlusion training

Yu Cheng, Bo Yang, Bo Wang, and Robby T. Tan

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2020

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images

Heming Zhu, Yu Cao, Hang Jin, Weikai Chen, Dong Du, Zhangye Wang, Shuguang Cui, Xiaoguang Han

European Conference on Computer Vision (ECCV), 2020, Oral Presentation

A General Differentiable Mesh Renderer for Image-based 3D Reasoning

Shichen Liu, Tianye Li, Weikai Chen, Hao Li

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020

Intuitive, Interactive Beard and Hair Synthesis with Generative Models

Kyle Olszewski, Duygu Ceylan, Jun Xing, Jose I. Echevarria, Zhili Chen, Weikai Chen, Hao Li

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Oral Presentation

Organic Open-cell Porous Structure Modeling

Lihao Tian, Lin Lu, Weikai Chen, Yang Xia, Charlie C. L. Wang and Wenping Wang

ACM Symposium on Computational Fabrication (ACM SCF), 2020

Hyperspectral Inverse Skinning

Liu, Songrun and Tan, Jianchao and Deng, Zhigang and Gingold, Yotam

Computer Graphics Forum, 39(6), 2020

Weavecraft: an interactive design and simulation tool for 3D weaving

Rundong Wu, Joy Xiaoji Zhang, Jonathan Leaf, Xinru Hua, Ante Qu, Claire Harvey, Emily Holtzman, Joy Ko, Brooks Hagan, Doug James, François Guimbretière, Steve Marschner.

ACM Transactions on Graphics (TOG) 39(6), 2020

Hierarchical optimization time integration for cfl-rate mpm stepping

Wang, Xinlei and Li, Minchen and Fang, Yu and Zhang, Xinxin and Gao, Ming and Tang, Min and Kaufman, Danny M and Jiang, Chenfanfu

ACM Transactions on Graphics (TOG) 39(3), 2020

Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

Kiwon Um, Robert Brand, Yun Fei, Philipp Holl, Nils Thuerey

In the Proceedings of Neural Information Processing Systems (NeurIPS) 2020