The Pattern Analysis and Computer Vision (PAVIS) research line is actively developing an artificial intelligence (AI) infrastructure to understand our physical space and the human behaviors within it.
The focus is on creating intelligent systems that jointly accomplish two main goals:
Pattern Analysis and Computer Vision
Spatial AI
Perceive and understand autonomously the real physical world, both static and dynamic, with its corresponding spatial semantic (where are things, what is their function, which is the dynamic of the scene).
Social AI
Perceive and understand humans and their behaviors as observed by cameras in relation to the physical spaces they are interacting with.
Relevant Papers
2025
Matteo B., Tsesmelis T., James S., Poiesi F., Del Bue A.
6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model
Lecture Notes in Computer Science, vol. 15110 LNCS, pp. 420-436
2025
Svitov D., Morerio P., Agapito L., Del Bue A.
BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
International Conference on Computer Vision
2025
Galliena T., Apicella T., Rosa S., Morerio P., Del Bue A., Natale L.
Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)
2025
Islam A., Fiorini S., James S., Morerio P., Del Bue A.
ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction
International Conference on Computer Vision
Principal Investigator
Pattern Analysis and Computer Vision
Videos
Intelligent Sensor Network for assistive AI Research
Introduction to MEMEX Project
Aworld - AI powered visual localization
PAVIS - Overview
SceneUnderLight - IIT - UNIVR - OSRAM
Drone Localization with Augmented Acoustic Imaging
IIT OpenTalk Magazine - Lab Highlights Show all >