Baixin Xu

I am a Ph.D. student at School of Computer Science and Engineering, Nanyang Technological University, supervised by Prof. Ying He.

I obtained my B.Eng. in Computer Science from Huazhong University of Science and Technology in 2022. My research journey has been deeply shaped by valuable industrial and academic collaborations. I spent time at SenseTime Research and the Shanghai AI Lab working with Dr. Kwan-Yee Lin, and have been fortunate to collaborate closely with Dr. Jiangbei Hu at NTU and Dr. Yangguang Li at Skywork AI.

Bridging 3D vision and generative AI to reconstruct, generate, and interactively edit digital worlds.

Email / Scholar / Github

Research (Selected | Full List)

I am interested in building 3D-aware visual systems that can reconstruct, edit, and generate high-quality geometry and immersive environments from sparse or multimodal inputs.

	Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory Zile Wang, Zexiang Liu, Jiaxing Li, Kaichen Huang, Baixin Xu, Fei Kang, Mengyin An, Peiyu Wang, Biao Jiang, Yichen Wei, Yidan Xietian, Jiangbo Pei, Liang Hu, Boyi Jiang, Hua Xue, Zidong Wang, Haofeng Sun, Wei Li, Wanli Ouyang, Xianglong He, Yang Liu, Yangguang Li, Yahui Zhou arXiv*, 2026 arXiv / project page / code
	AquaSplatting: A Hybrid 3D Representation for Robust Underwater Scene Reconstruction via Dual-Branch Rendering Jiangbei Hu, Haobo Wang, Baixin Xu, Nan Ding, Zhimao Lu, Na Lei, Ying He AAAI, 2026
	Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling Hongyang Wei, Hongbo Liu, Zidong Wang, Yi Peng, Baixin Xu, Size Wu, Xuying Zhang, Xianglong He, Zexiang Liu, Peiyu Wang, Xuchen Song, Yangguang Li, Yang Liu, Yahui Zhou arXiv, 2026 arXiv
	Matrix-Game 2.0: An Open-Source Real-Time and Streaming Interactive World Model Xianglong He, Chunli Peng, Zexiang Liu, Boyang Wang, Yifan Zhang, Qi Cui, Fei Kang, Biao Jiang, Mengyin An, Yangyang Ren, Baixin Xu, Hao-Xiang Guo, Kaixiong Gong, Size Wu, Wei Li, Xuchen Song, Yang Liu, Yangguang Li, Yahui Zhou arXiv, 2025 arXiv / project page
	Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model Hongyang Wei, Baixin Xu, Hongbo Liu, Size Wu, Jie Liu, Yi Peng, Peiyu Wang, Zexiang Liu, Jingwen He, Yidan Xietian, Chuanxin Tang, Zidong Wang, Yichen Wei, Liang Hu, Boyi Jiang, Wei Li, Ying He, Yang Liu, Xuchen Song, Yangguang Li, Yahui Zhou arXiv*, 2025 arXiv
	Matrix-3D: Omnidirectional Explorable 3D World Generation Zhongqi Yang, Wenhang Ge, Yuqi Li, Jiaqi Chen, Haoyuan Li, Mengyin An, Fei Kang, Hua Xue, Baixin Xu, Yuyang Yin, Eric Li, Yang Liu, Yikai Wang, Hao-Xiang Guo, Yahui Zhou arXiv, 2025 arXiv / project page / code
	TopoGen: Topology-Aware 3D Generation with Persistence Points Jiangbei Hu, Ben Fei, Baixin Xu, Fei Hou, Shengfa Wang, Na Lei, Weidong Yang, Chen Qian, Ying He Computer Graphics Forum (Pacific Graphics), 2025 paper
	MGSR: 2D/3D Mutual-Boosted Gaussian Splatting for High-Fidelity Surface Reconstruction under Various Light Conditions Qingyuan Zhou, Yuehu Gong, Weidong Yang, Jiaze Li, Yeqi Luo, Baixin Xu, Shuhao Li, Ben Fei, Ying He ICCV, 2025 arXiv
	Do Not Deepfake Me: Privacy-Preserving Neural 3D Head Reconstruction without Sensitive Images Jiayi Kong, Xurui Song, Shuo Huai, Baixin Xu, Jun Luo, Ying He AAAI, 2025 arXiv
	SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images Daisheng Jin, Jiangbei Hu, Baixin Xu, Yuxin Dai, Chen Qian, Ying He CVPR, 2025 paper / project page / code
	Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering Baixin Xu Jiangbei Hu, Fei Hou, Kwan-Yee Lin, Wayne Wu, Chen Qian, Ying He ECCV, 2024 project page / arXiv
	GSurf: 3D Reconstruction via Signed Distance Fields with Direct Gaussian Supervision Baixin Xu, Jiangbei Hu, Jiaze Li, Ying He arXiv, 2024 arXiv
	IF-TONIR: Iteration-Free Topology Optimization Based on Implicit Neural Representations Jiangbei Hu, Ying He, Baixin Xu, Shengfa Wang, Na Lei, Zhongxuan Luo Computer-Aided Design, 2024 paper / code
	Deformable Model Driven Neural Rendering for High-fidelity 3D Reconstruction of Human Heads Under Low-View Settings Baixin Xu, Jiarui Zhang, Kwan-Yee Lin, Chen Qian, Ying He ICCV, 2023 paper / code / arXiv a deformable model and a coarse-to-fine training strategy to reconstruct human heads from limited views.

Experiences

Research Engineer (IPP), Skywork AI, 2024 - 2026
Topic: interactive world models and unified multimodal generation.

Research Intern, Shanghai AI Laboratory, 2022 - 2023
Worked with Dr. Kwan-Yee Lin on neural head reconstruction and rendering.

Services

Conference reviewer:
CVPR (2024/2025), ECCV (2024), ICCV (2025), NeurIPS (2025), ACM Multimedia (2024), AAAI (2025/2026), ICLR (2025), Pacific Graphics (2023/2024).

Journal reviewer:
Computational Visual Media (CVM-J), IEEE Transactions on Visualization and Computer Graphics (TVCG), IEEE Transactions on Image Processing (TIP), IEEE Computer Graphics and Applications, The Visual Computer.

Selected Honors & Awards

Outstanding Graduate of Huazhong University of Science and Technology, 2022.

Misc

I enjoy building practical visual systems, learning from elegant geometry, and collaborating across vision, graphics, and generative modeling.

Website template adapted from Jon Barron's website.