Fanpeng Meng

Fanpeng Meng | 孟繁鹏

I am an Engineer at Huawei Inc. and a core member of the Xiaoyi 3D Team, working under the leadership of Dr. Jiemin Fang and Dr. Qi Tian.

Prior to that, I received an M.Phil. in Computer & Information Engineering from The Chinese University of Hong Kong (Shenzhen), advised by Prof. Xiaoguang Han. Before that, I obtained a B.Eng. from Huazhong University of Science & Technology, and once worked with Prof. He Wang from Peking University.

Research Interests: My research focuses on 3D AIGC & World Models. I aspire to build high-quality, practical, and efficient 3D digital worlds towards the AGI era.

Email / Google Scholar / GitHub

News

2026-10: PhysAg3D is now available, turning a single image into a high-fidelity, physically interactive 3D asset! Webpage / Paper / Code.
2026-10: SUPRA-Tex is fully open source, turning a single image into a 3D asset with reference-aligned PBR textures — trained only on open-source data, yet preferred over five commercial systems in human evaluations! Webpage / Paper / Code / Weights / Demo.
2026-06: Xiaoyi 3D × Pixel Artisan PRO, developed by our Xiaoyi 3D Team, debuted at HDC 2026 and won the HarmonyOS Innovative Premium App Award.
2025-11: I joined Huawei Inc. as an Engineer, working under the leadership of Dr. Jiemin Fang & Dr. Qi Tian.
2025-06: I received an M.Phil. from The Chinese University of Hong Kong (Shenzhen), advised by Prof. Xiaoguang Han.

Research [*] equal contribution; [^†] corresponding author(s); [^‡] project lead; Representative papers are highlighted.
	PhysAg3D: Bridging 3D Generative and Agentic Models for High-Fidelity and Physically-Interactive Assets Bi'an Du, Fanpeng Meng, Jiemin Fang^‡†, Chen Yang, Pufan Li, Daizong Liu, Qi Tian^†, Wei Hu^† arXiv, 2026 Combining 3D generation and agentic reasoning to turn a single image into high-fidelity 3D assets with rigid articulation and compliant deformation. An agent harness guides refinement while preserving geometry and materials. Webpage / Paper / Code
	SUPRA-Tex: 3D Generation with Super-Aligned Texture Chen Yang, Jiemin Fang^†, Fanpeng Meng, Zihao Huang, Jichen Pang, Guanjun Wu, Zhikuan Bao, Qi Tian^† arXiv, 2026* · Fully open source From a single image, generating 3D assets with reference-aligned PBR textures that preserve fine lettering, patterns, and material details. Trained only on open-source data, it is preferred over five commercial systems, Hunyuan3D 3.1, Rodin 2.5, Tripo H3.1, Meshy 7.1, and Hi3D 3.0, for both visual quality and input alignment across 512 paired human evaluations. Webpage / Paper / Code / Weights / Demo
	Gate3DGen: A Pre-processing Model that Selectively Purifies Real-World Images for 3D Generation Xiaolin Li, Zihao Huang, Fanpeng Meng, Chen Yang, Guanjun Wu, Kai Zhang^†, Jiemin Fang^†, Qi Tian^† arXiv, 2026 Webpage / Paper / Code Reducing blur, occlusion, and other image degradations while preserving object identity and details, providing higher-quality inputs for 3D generation.