Mixed Reality Environment for Immersive Experience of Art and Culture

Informazioni relative al progetto

XTREME

ID dell’accordo di sovvenzione: 101136006

DOI

10.3030/101136006

Data della firma CE 14 Novembre 2023

Data di avvio 1 Gennaio 2024

Data di completamento 31 Dicembre 2026

Finanziato da

• Digital, Industry and Space

Costo totale

€ 7 255 954,74

Contributo UE

€ 7 255 953,75

Coordinato da

IT-UNIVERSITETET I KOBENHAVN
Denmark

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Data Management Plan (2)

Data Management Plan

Data Management Plan (first version): DMP will document processes for collecting, storing, and sharing data which will continuously be updated

Data Management Plan (update)

Updated DMP

Documents, reports (5)

Dissemination and Exploitation Plan

Dissemination and Exploitation Plan: Plan for dissemination and exploitation including communication activities, website

User requirements and hardware

User requirements and hardware: Identification of user requirements and selection of hardware for XTREME

3D human models

3D human models: Real-time motion capture, fine grain pose and gesture reconstruction

Audio localisation model

Audio localisation model: Audio perceptual localisation by physical cues, and visual models from audio

XR Regulation report

XR Regulation report: XR, data, AI and regulation assessing emerging risks about basic principles in use of data in AI/XR

Other (1)

API

API: Definition of the overall system architecture and a common software interface API that will be used as the basis for XTREME methods

Demonstrators, pilots, prototypes (1)

Bubble service models

Bubbles service models: Prototype and evaluation of the Bubbles social interaction service

Pubblicazioni

Conference proceedings (8)

In the middle of the music: A qualitative study of headset and loudspeaker distributed interactive spatial audio within a musical mixed-reality environment

Autori: Laurence Cliffe, M. Khan, Steve Benford.
Pubblicato in: Audio Mostly 2025, 2025
Editore: Audio Mostly 2025

QPM: DISCRETE OPTIMIZATION FOR GLOBALLY INTERPRETABLE IMAGE CLASSIFICATION

Autori: Thomas Norrenbrock, Timo Kaiser, Sovan Biswas, Ramesh Manuvinakurike, Bodo Rosenhahn
Pubblicato in: Proceedings of the International Conference on Learning Representations (ICLR 2025), 2025
Editore: International Conference on Learning Representations (ICLR) 2025

Multimodal Rationales for Explainable Visual Question Answerin

Autori: Kun Li, George Vosselman, Michael Ying Yang
Pubblicato in: 2025
Editore: IEEE

Navigating the Virtual Gaze: Social Anxiety's Role in VR Proxemics

Autori: Beatriz Mello, Robin Welsch, Marissa Christien Verbokkem, Pascal Knierim, Martin Johannes Dechant
Pubblicato in: Proceedings of the CHI Conference on Human Factors in Computing Systems, 2025
Editore: ACM
DOI: 10.1145/3613904.3642359

Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery

Autori: Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn, Bastian Wandt
Pubblicato in: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Editore: IEEE
DOI: 10.1109/WACV61041.2025.00571

UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model

Autori: Timo Kaiser; Thomas Norrenbrock; Bodo Rosenhahn
Pubblicato in: 2025
Editore: International Conference on Machine Learning (ICML 2025)

"""AI enhances our performance, I have no doubt this one will do the same"": The Placebo effect is robust to negative descriptions of AI"

Autori: Agnes Mercedes Kloft, Robin Welsch, Thomas Kosch, Steeven Villa
Pubblicato in: Proceedings of the CHI Conference on Human Factors in Computing Systems, 2025
Editore: ACM
DOI: 10.1145/3613904.3642633

Multi‑Flow: Multi‑View‑Enriched Normalizing Flows for Industrial Anomaly Detection

Autori: Mathis Kruse, Bodo Rosenhahn
Pubblicato in: 2025
Editore: Computer Vision Foundation via the CVPR Workshops proceedings
DOI: 10.48550/ARXIV.2504.03306

Peer reviewed articles (5)

Don't They Really Hear Us? A Design Space for Private Conversations in Social Virtual Reality

Autori: Josephus Jasper Limbago, Robin Welsch, Florian Müller, Mario Di Francesco
Pubblicato in: IEEE Transactions on Visualization and Computer Graphics, Numero 31, 2025, ISSN 1077-2626
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TVCG.2025.3549844

Scale-wise Bidirectional Alignment Network for referring remote sensing image segmentation

Autori: Kun Li, George Vosselman, Michael Ying Yang
Pubblicato in: ISPRS Journal of Photogrammetry and Remote Sensing, Numero 226, 2025, ISSN 0924-2716
Editore: Elsevier BV
DOI: 10.1016/J.ISPRSJPRS.2025.05.014

Into the Here and Now: Explorations within a New Acoustic Virtual Reality

Autori: Laurence Cliffe
Pubblicato in: Leonardo, Numero 58, 2025, ISSN 0024-094X
Editore: MIT Press
DOI: 10.1162/LEON_A_02651

Attribute-Centric Compositional Text-to-Image Generation

Autori: Yuren Cong, Martin Renqiang Min, Li Erran Li, Bodo Rosenhahn, Michael Ying Yang
Pubblicato in: International Journal of Computer Vision, Numero 133, 2025, ISSN 0920-5691
Editore: Springer Science and Business Media LLC
DOI: 10.1007/S11263-025-02371-0

Interfacing with history: curating with audio augmented objects

Autori: Laurence Cliffe
Pubblicato in: Museum Management and Curatorship, 2024, ISSN 0964-7775
Editore: Informa UK Limited
DOI: 10.1080/09647775.2024.2431899

Thesis and dissertations (1)

Learning Of Room Audio Response Employing Sound Directional Information

Autori: GiovanniI Zanin
Pubblicato in: 2025
Editore: UNIVERSITY OF TRIESTE