MEDIA LAB

We are pleased to announce that the paper “MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities” has been accepted at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) held in Nashville, Tennessee. This work is the latest successful result of our long-lasting collaboration with the Stuttgart Technology Center of Sony Europe. Congratulations… Read more: Paper accepted @ CVPR 2025

We will present 3 papers (2 at the main conference and a workshop one) at the European Conference on Computer Vision (ECCV) : “HoloADMM: High-Quality Holographic Complex Field Recovery” (in collaboration with Sony Europe) and “Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation” (in collaboration with the Xidian University) at the main conference. Furthermore we will… Read more: 3 MEDIALAB papers @ ECCV

MEDIA Lab is participating to a new three-year EU project, Hybrid Extended reAliTy (HEAT). HEAT aims at integrating immersive media technologies such as point cloud/holographic imaging, multi-sensorial media, Social VR in a multi-user, feedback-enabled communication system to provide the construction of compelling context-aware and embodied experiences for innovative hybrid XR applications.

We are happy to announce that the paper “Learning with Style: Continual Semantic Segmentation Across Tasks and Domains” from Marco Toldo, Umberto Michieli and Pietro Zanuttigh has been accepted for publication on the IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).

We are happy to announce that the paper “ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data” from Carmen Martin-Turrero, Maxence Bouvier, Manuel Breitenstein, Pietro Zanuttigh and Vincent Parret has been accepted for publication at the International Conference on Machine Learning (ICML). The work is a result of the long-term collaboration we have with Sony EuTEC.

We presented 2 papers at the ACM Multimedia Systems Conference. : “A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation” (research track) and “Questset: A VR Dataset for Network and Quality of Experience Studies” (software and dataset track) The first work has been possible thanks to a collaboration between the MEDIA Lab and Samsung Research… Read more: 2 Papers at ACM MMSys 2024