X2Real: an eXtensive simulation benchmark for real-world generalist policies
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 Images
IEEE International Conference on Multimedia & Expo (ICME), 2025
DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidance
IEEE International Conference on Multimedia & Expo (ICME), 2025
UniFaceGAN: High-Quality 3D Face Editing with a Unified Latent Space
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Neural Global Illumination: Interactive Indirect Illumination Prediction under Dynamic Area Lights
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022
Deferred Neural Lighting: Free-viewpoint Relighting from Unstructured Photographs
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2020
PDF (Low Resolution) PDF (High Resolution) Supplementary Video Slides Code BibTeX
Deep Inverse Rendering for High-resolution SVBRDF Estimation from an Arbitrary Number of Images
ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2019
PDF (Low Resolution) PDF (High Resolution) Supplementary Video Slides Code BibTeX
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.
