CVTS 2026

    The Computer Vision Trento Symposium (CVTS), organised by FBK, brings together scientists, researchers, students, practitioners, and enthusiasts who share an interest in computer vision.
    20/05/2026 | 09:00 — 16:00

    Sala “Luigi Stringa”, FBK Povo

    Via Sommarive 18, Povo

    CVTS 2026 features an especially rich program, with 17 outstanding papers selected for CVPR 2026 in Denver. The event will include six technical sessions focused on some of the hottest topics in Computer Vision: Generative AI and realistic scene synthesis, 3D representations, Vision-Language Model applications and grounded reasoning, bias and model safety, interpretability, and transfer learning.

    Program:

    9.00 Welcome + IT4LIA AI Factory project

    Fabio Poiesi & Luigi Riz

    9.20
    Keynote: The making of Blender
    Francesco Siddi, CEO of Blender
    Francesco Siddi will walk us through his own experience coming up through the Blender community and will share how the Blender was built into a public, community-centric project.
    10.20

     Session 1: Generative AI

    A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation

    Wentao Qu, Guofeng Mei, Yang Wu, Yongshun Gong, Xiaoshui Huang, Liang Xiao

    MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection

    Jinwei Hu, Francesco Borsatti, Arianna Stropeni, Davide Dalle Pezze, Manuel Barusco, Gian Antonio Susto

    Q&A
    10.45 IT4LIA AI Factory Coffee Break
    11.15
    Session 2: Bias, safety & interpretability
    From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition

    Francesco Gentile, Nicola Dall’Asen, Francesco Tonini, Massimiliano Mancini, Lorenzo Vaquero, Elisa Ricci

    Q&A
    11.45
    Session 3: 3D representations
    Efficient Encoder-Free Fourier-based 3D Large Multimodal Model

    Guofeng Mei, Wei Lin, Luigi Riz, Yujiao Wu, Yiming Wang, Fabio Poiesi

    BEA-GS : BEyond RAdiance Supervision in 3DGS for Precise Object Extraction

    Alessio Mazzucchelli, María Naranjo Almeida, Jorge Bustos Sanchez, Mariella Dimiccoli, Francesc Moreno-Noguer, Jordi Sanchez-Riera, Adrian Penate-Sanchez

    Haptic Neural Fields: Bringing Tactile Interactions to 3D Rendered Scenes

    Antonio Luigi Stefani, Niccolò Bisagno, Nicola Conci, Eckehard Steinbach, Francesco GB De Natale

    Universal 3D Shape Matching via Coarse-to-Fine Language Guidance

    Qinfeng Xiao, Guofeng Mei, Bo Yang, Liying Zhang, Jian Zhang, Kit-lun Yick

    Q&A

    12.25 IT4LIA AI Factory Lunch + Posters

    14.25
    Session 4: Grounded reasoning
    Obstruction reasoning for robotic grasping

    Runyu Jiao, Matteo Bortolon, Francesco Giuliari, Alice Fasoli, Sergio Povoli, Guofeng Mei, Yiming Wang, Fabio Poiesi

    TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

    Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota

    Q&A
    14.50
    Session 5: VLM applications
    StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues

    Zanxi Ruan, Songqun Gao, Qiuyu Kong, Yiming Wang, Marco Cristani

    How to Take a Memorable Picture? Empowering Users with Actionable Feedback

    Francesco Laiti, Davide Talon, Jacopo Staiano, Elisa Ricci

    ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

    Alberto Compagnoni, Marco Morini, Sara Sarto, Federico Cocchi, Davide Caffagni, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

    Q&A
    15.35
    Session 6: Transfer learning
    CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation

    Mainak Singha, Sarthak Mehrotra, Paolo Casari, Subhasis Chaudhuri, Elisa Ricci, Biplab Banerjee

    Specificity-aware reinforcement learning for fine-grained open-world classification

    Samuele Angheben, Davide Berasi, Alessandro Conti, Elisa Ricci, Yiming Wang

    The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

    Haiyang Zheng, Nan Pu, Yaqi Cai, Teng Long, Wenjing Li, Nicu Sebe, Zhun Zhong

    Q&A
    16.10 Closing

    Fabio Poiesi

     Conference Website

    Related Media
    Privacy Notice
    Pursuant to art. 13 of EU Regulation No. 2016/679 – General Data Protection Regulation and as detailed in the Privacy Policy for FBK event’s participants, we inform you that the event will be recorded and disclosed on the FBK institutional channels. In order not to be filmed or recorded, you can disable the webcam and/or mute the microphone during virtual events or inform the FBK staff who organize the public event beforehand.