Selected Publications

See the full list on my Google Scholar.

†Equal Contribution, *Corresponding Author(s)

These are the current publications from my Google Scholar profile, sorted by publication date.

  1. Obstruction reasoning for robotic grasping
    R Jiao, M Bortolon, F Giuliari, A Fasoli, S Povoli, G Mei, Y Wang, F Poiesi
    2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2026)
    Google Scholar
  2. Action-guided generation of 3D functionality segmentation data
    J Corsetti, F Giuliari, D Boscaini, P Hermosilla, A Pilzer, G Mei, A Delitzas, ...
    2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops …
    Google Scholar
  3. A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
    W Qu, G Mei, Y Wu, Y Gong, X Huang, L Xiao
    2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2026)
    Google Scholar
  4. The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report
    B Ren, H Guo, Y Shu, J Ma, Z Cui, S Liu, G Mei, L Sun, Z Wu, FS Khan, ...
    NTIRE Workshop and Challenges CVPR 2026
    Google Scholar
  5. GLASS: Graph and Vision-Language Assisted Semantic Shape Correspondence
    Q Xiao, G Mei, Q Liu, C Yi, F Poiesi, J Zhang, B Yang, Y Kit-lun
    2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR …)
    Google Scholar
  6. Efficient Encoder-Free Fourier-based 3D Large Multimodal Model
    G Mei, W Lin, L Riz, Y Wu, Y Wang, F Poiesi
    2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2026)
    Google Scholar
  7. Universal 3D Shape Matching via Coarse-to-Fine Language Guidance
    Q Xiao, G Mei, B Yang, L Zhang, J Zhang, K Yick
    2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2026)
    Google Scholar
  8. Masked Clustering Prediction for Unsupervised Point Cloud Pre-training
    B Ren, X Huang, M Liu, H Liu, F Poiesi, N Sebe, G Mei
    Annual AAAI Conference on Artificial Intelligence (Oral, AAAI)
    Google Scholar
  9. Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion
    W Qu, G Mei, J Wang, Y Wu, X Huang, L Xiao
    Annual AAAI Conference on Artificial Intelligence (AAAI)
    Google Scholar
  10. PISI: Physical Information Based Solver-Interactive Network Structure Reconstruction
    J Liu, G Mei
    Algorithms 18 (9), 584
    Google Scholar
  11. PerLA: Perceptive 3D language assistant
    G Mei, W Lin, L Riz, Y Wu, F Poiesi, Y Wang
    2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    Google Scholar
  12. Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding
    G Mei, B Ren, J Liu, L Riz, X Huang, X Zheng, Y Gong, MH Yang, N Sebe, ...
    arXiv preprint arXiv:2505.18819
    Google Scholar
  13. Adversarial robustness for unified multi-modal encoders via efficient calibration
    CT Liao, Z Chen, C Meng, TY Huang, X Cao, X Zheng
    arXiv preprint arXiv:2505.11895
    Google Scholar
  14. TVEG: Model Selection of the Time-Varying Exponential Family Distributions Graphical Models
    J Liu, G Mei, Y Xia, X Wu, J Lü
    IEEE Transactions on Network Science and Engineering
    Google Scholar
  15. Free-form language-based robotic reasoning and grasping
    R Jiao, A Fasoli, F Giuliari, M Bortolon, S Povoli, G Mei, Y Wang, F Poiesi
    IROS 2025
    Google Scholar
  16. PointGAC: Geometric-Aware Codebook for Masked Point Modeling
    A Li, C Lv, Y Fang, Y Zuo, J Zhang, G Mei
    Proceedings of the IEEE/CVF International Conference on Computer Vision …
    Google Scholar
  17. Fully-Geometric Cross-Attention for Point Cloud Registration
    W Wang, G Mei, J Zhang, N Sebe, B Lepri, F Poiesi
    International Conference on 3D Vision (3DV)
    Google Scholar
  18. Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant
    G Mei, L Riz, Y Wang, F Poiesi
    International Conference on 3D Vision (3DV)
    Google Scholar
  19. Multimodal fusion SLAM with Fourier attention
    Y Zhou, G Mei, Y Wang, Y Wan, F Poiesi
    IEEE Robotics and Automation Letters 10 (2), 1050-1057
    Google Scholar
  20. GSTran: Joint Geometric and Semantic Coherence for Point Cloud Segmentation
    A Li, C Lv, G Mei, Y Zuo, J Zhang, Y Fang
    ICPR 2024
    Google Scholar