X2Real: an eXtensive simulation benchmark for real-world generalist policiesPDF
arXiv preprint arXiv:2609.27449, 2026
I am a computer graphics researcher. I received my Ph.D. in Computer Science from Tsinghua University in 2022, advised by Prof. Kun Xu, and my bachelor's degree in Computer Science from Nanjing University in 2017.
Previously, I was a Principal Engineer in the Top Minds Program at Huawei Cloud Media Innovation Lab, where I worked on generative 3D digital humans, diffusion-based material generation, AIGC-3D, and differentiable rendering. I am currently at X Square Robot, working on simulation, data generation, and learning algorithms for embodied AI.
Research interests
Appearance modeling, Physically based rendering, Neural rendering, Differentiable rendering, 3D generative modeling
Services & Awards
Academic Services
Reviewer for SIGGRAPH 2022/2025, SIGGRAPH Asia 2023/2025, Eurographics, Pacific Graphics, The Visual Computer, Journal of Computer-Aided Design & Computer Graphics
Selected Awards
- 2022, Huawei Top Minds Program
- 2022, Outstanding Graduate of Beijing
- 2022, Outstanding Doctoral Graduate at Tsinghua University
- 2021, Style3D Graduate Fellowship
- 2019, Star of Tomorrow Intern Award at Microsoft Research Asia
Publications
ControlFace: Few-Shot 3D Face Generation via a Controllable Diffusion Model Guided by Text and ImagesPDF
IEEE International Conference on Multimedia & Expo (ICME), 2025
DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal GuidancePDF
IEEE International Conference on Multimedia & Expo (ICME), 2025
UniFaceGAN: High-Quality 3D Face Editing with a Unified Latent SpacePDF
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Neural Global Illumination: Interactive Indirect Illumination Prediction under Dynamic Area LightsPDF
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022
Deferred Neural Lighting: Free-viewpoint Relighting from Unstructured PhotographsPDF
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2020
Deep Inverse Rendering for High-resolution SVBRDF Estimation from an Arbitrary Number of ImagesPDF
ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2019
Thesis
Neural Rendering: Deep Learning Based Photorealistic Rendering
基于深度学习的真实感渲染研究
Supervisor: Kun Xu
A Learning-Based Rendering Algorithm for Translucent Materials
(基于学习的)高逼真半透明材质的渲染方法
Supervisor: Kun Xu, Jie Guo
Experience
-
2025-Present
Embodied AI Simulation Engineer
X Square Robot
Developing simulation data platforms for embodied AI, spanning Sim-Ready asset generation, diverse scene construction, data augmentation, data production, and algorithm optimization for embodied models.
-
2022-2025
Principal Engineer, Top Minds (天才少年)
Huawei Cloud, Media Innovation Lab
Worked on generative 3D digital humans, diffusion-based material generation, AIGC-3D, and differentiable rendering.
-
2019.10-2020.5
Research Intern
Microsoft Research Asia, Internet Graphics Group
Conducted research on neural relighting with Dr. Guojun Chen, Dr. Yue Dong, and Dr. Xin Tong.
-
2019.7-2019.8
Research Intern
Tencent AI Lab
Conducted research on 3D face reconstruction with Dr. Haozhi Huang.
-
2018.8-2019.5
Research Intern
Microsoft Research Asia, Internet Graphics Group
Conducted research on appearance modeling with Dr. Yue Dong and Dr. Xin Tong.
-
2017.7-2017.9
Research Intern
Megvii (Face++)
Conducted research on facial recovery and rendering with Dr. Liqian Ma.
