Curriculum Vitae
Guofeng (Ryan) Mei · Researcher in 3D Computer Vision, Machine Learning, and Deep Learning
Profile
I am a researcher at Fondazione Bruno Kessler (FBK), Technologies of Vision (TeV), Trento, Italy. My research focuses on 3D vision-language models, 3D scene understanding, point cloud registration and representation learning, embodied AI, and efficient learning.
Work and Research Experience
Researcher
Fondazione Bruno Kessler, Trento, Italy
- Conduct research in AI, 3D vision, and vision-language models.
- Develop and evaluate models for 3D scene understanding and multimodal learning.
- Supervise Ph.D. students and support junior researchers.
Ph.D. Researcher
University of Technology Sydney, Sydney, Australia
- Researched robust 3D point cloud registration, correspondence estimation, and geometric feature learning.
- Designed unsupervised learning methods for 3D point cloud representation learning.
Algorithm Engineer roles
Xiaomi Corporation, Mogu Inc., ZTE Corporation, and Eisoo Ltd.
- Worked on NLP, recommendation, search, anomaly detection, distributed data processing, and computer vision applications.
Education
Ph.D. in Computer Science
University of Technology Sydney, Australia. Thesis: Robust 3D Point Cloud Registration Based on Deep Learning and Optimization. Supervisor: Prof. Jian Zhang.
Visiting Ph.D. Student
University of Trento, Italy. Research topic: Unsupervised 3D Point Cloud Representation Learning. Supervisor: Prof. Nicu Sebe.
M.Sc. in Computational Mathematics
Wuhan University, China. Thesis: Optimization-based Structure Identification in Complex Networks. Supervisor: Prof. Xiaoqun Wu.
Selected Publications
- Guofeng Mei, Wei Lin, Luigi Riz, Yujiao Wu, Fabio Poiesi, Yiming Wang. Efficient Encoder-Free Fourier-based 3D Large Multimodal Model. CVPR, 2026.
- Qinfeng Xiao†, Guofeng Mei†, Bo Yang, Liying Zhang, Jian Zhang, Kit-lun Yick. Universal 3D Shape Matching via Coarse-to-Fine Language Guidance. CVPR, 2026.
- Wentao Qu†, Guofeng Mei†, Yang Wu, Yongshun Gong, Xiaoshui Huang, Liang Xiao. A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation. CVPR, 2026.
- Guofeng Mei, Wei Lin, Luigi Riz, Yujiao Wu, Fabio Poiesi, Yiming Wang. PerLA: Perceptive 3D Language Assistant. CVPR, 2025.
- Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi. Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant. 3DV, 2025.
- Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi. Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding. CVPR Highlight, 2024.
- Guofeng Mei, Hao Tang, Juan Liu, Xiaoshui Huang, Jian Zhang, Qiang Wu, Luc Van Gool. Unsupervised Probabilistic Approach for Point Cloud Registration. CVPR, 2023.
- Guofeng Mei, Cristiano Saltori, Fabio Poiesi, Elisa Ricci, Nicu Sebe, Qiang Wu, Jian Zhang. Unsupervised Point Cloud Representation Learning by Clustering and Neural Rendering. IJCV, 2024.
†Equal contribution. See the publications page for a longer list.
Skills
Programming: Python, C/C++, Java, Scala, MATLAB
Libraries: PyTorch, TensorFlow, Scikit-learn, NumPy, OpenCV, Open3D
Data and tools: Apache Spark, Hadoop, Hive, MySQL, Microsoft SQL Server, Redis
Development: Git, Docker, SLURM, Linux, macOS, Windows, LaTeX
Languages: English and Mandarin Chinese
Honors and Awards
- Silver Reviewer, ICML Program Committee, 2026.
- Outstanding Reviewer, ICCV Program Committee, 2025.
- Outstanding Reviewer, CVPR Program Committee, 2025 and 2024.
- UTS International Research Scholarship and UTS President's Scholarship, 2019-2023.
- National Scholarship for Graduate Students, China, 2014.
Professional Service
Journal reviewer: TPAMI, TIP, TMM, TMC, TVCG, TCSVT, CIM, RA-L, PR, and CVIU.
Conference reviewer: CVPR, ICCV, ICML, ICLR, NeurIPS, ECCV, ACM MM, ICRA, WACV, BMVC, ICME, ICASSP, and IROS.