Language Augmentation for Humanverse

Información del proyecto

LUMINOUS

Identificador del acuerdo de subvención: 101135724

DOI

10.3030/101135724

Fecha de la firma de la CE 23 Octubre 2023

Fecha de inicio 1 Enero 2024

Fecha de finalización 31 Diciembre 2026

Financiado con arreglo a

• Digital, Industry and Space

Coste total

€ 5 603 706,25

Aportación de la UE

€ 5 603 706,25

Coordinado por

DEUTSCHES FORSCHUNGSZENTRUM FUR KUNSTLICHE INTELLIGENZ GMBH
Germany

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Documents, reports (7)

Intermediate report on virtual avatar rendering and animation

This first report presents the results and approached developed for the creation of realistic avatar rendering using hybrid structures (mesh + neural rendering).

Report on the identification of evaluation metrics and dataset collections

The report presents the collected MLLM datasets, which will be used for the system development and tests, and later for the trials.Moreover it will propose a meaningful metric for the evaluation of the implemented neural networks.

LUMINOUS Impact Master Plan

"The report ""LUMINOUS Impact Master Plan"" defines the strategy and measures for ensuring the maximum impact of the project. This includes dissemination and communication strategy (Communication and Dissemination Plan), identification of synergy effects with other related projects and a first Exploitation Plan."

POPD - Requirement No. 2

The report presents the requirements related to the Protection of Personal Data of the persons involved in the trials. This will include the description of the anonymisation/pseudonymisation techniques that will be implemented in the project and all related compliance issues to safeguard the rights of the subjects.

Trustworthy AI - Requirement No. 3

The deliverable provides an overview of the investigation of the framework for LUMINOUS applications for compliance with Trustworthy AI.

Humans(H) - Requirement No. 1

The deliverable present the details about how the consent of the participants will be acquired in accordance with the regulations and ethics principles.

LUMINOUS Dissemination and Communication Interim Report

The report provides a mid-term overview of the reached dissemination and communication activities and will be use to refine the overall strategy.

Publicaciones

Conference proceedings (13)

Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection

Autores: Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
Publicado en: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editor: IEEE
DOI: 10.1109/CVPR52733.2024.00558

PixT3: Pixel-based Table-To-Text Generation

Autores: Iñigo Alonso, Eneko Agirre, Mirella Lapata
Publicado en: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
Editor: Association for Computational Linguistics
DOI: 10.18653/V1/2024.ACL-LONG.364

Compact 3D Scene Representation via Self-Organizing Gaussian Grids

Autores: Wieland Morgenstern, Florian Barthel, Anna Hilsmann, Peter Eisert
Publicado en: European Conference on Computer Vision (ECCV 2024), 2024
Editor: Springer Science+Business Media
DOI: 10.1007/978-3-031-73013-9_2

STEP-DETR: Advancing DETR-based Semi-Supervised Object Detection with Super Teacher and Pseudo-Label Guided Text Queries

Autores: Tahira Shehzadi, Khurram Azeem Hashmi, Shalini Sarode, Didier Stricker, Muhammad Zeshan Afzal
Publicado en: International Conference on Computer Vision, ICCV 2025, 2025
Editor: IEEE Computer Society in cooperation with the Computer Vision Foundation (CVF)

Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts

Autores: Mohammad Sadil Khan, Sankalp Sinha, Talha Uddin Sheikh, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
Publicado en: NeurIPS 2024 - Neural Information Processing Systems, 2024
Editor: Curran Associates

Multi-Resolution Generative Modeling of Human Motion from Limited Data

Autores: David Eduardo Moreno-Villamarin, Anna Hilsmann, Peter Eisert
Publicado en: Proceedings of 21st ACM SIGGRAPH Conference on Visual Media Production, 2025
Editor: ACM
DOI: 10.1145/3697294.3697309

Improving Adaptive Density Control for 3D Gaussian Splatting

Autores: Glenn Grubert, Florian Barthel, Anna Hilsmann, Peter Eisert
Publicado en: Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2025
Editor: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0013308500003912

Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks

Autores: Florian Barthel, Arian Beckmann, Wieland Morgenstern, Anna Hilsmann, Peter Eisert
Publicado en: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024
Editor: IEEE
DOI: 10.1109/CVPRW63382.2024.00794

Realtime-Rendering of Dynamic Scenes with Neural Radiance Fields

Autores: Kilian L. Krause, Wieland Morgenstern, Anna Hilsmann, Peter Eisert
Publicado en: 2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 2025
Editor: IEEE
DOI: 10.1109/VRW66409.2025.00345

Conversational Tutoring in VR Training: The Role of Game Context and State Variables

Autores: Maia Aguirre, Ariane Méndez, Aitor García-Pablos, Montse Cuadros, Arantza del Pozo, Oier Lopez de Lacalle, Ander Salaberria, Jeremy Barnes, Pablo Martínez, Muhammad Zeshan Afzal
Publicado en: 15th International Workshop on Spoken Dialogue Systems Technology, 2025
Editor: Association for Computational Linguistics

MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation

Autores: Sankalp Sinha, Mohammad Sadil Khan, Muhammad Usama, Shino Sam, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
Publicado en: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Editor: IEEE
DOI: 10.1109/CVPR52734.2025.00759

BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval

Autores: Imanol Miranda, Ander Salaberria, Eneko Agirre, Gorka Azkune
Publicado en: NeurIPS 2024 - Neural Information Processing Systems, 2024
Editor: Curran Associates

Vision-Language Models Struggle to Align Entities across Modalities

Autores: Iñigo Alonso, Gorka Azkune, Ander Salaberria, Jeremy Barnes, Oier Lopez De Lacalle
Publicado en: Findings of the Association for Computational Linguistics: ACL 2025, 2025
Editor: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-ACL.965

Peer reviewed articles (2)

3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods

Autores: M. T. Bagdasarian, P. Knoll, Y. Li, F. Barthel, A. Hilsmann, P. Eisert, W. Morgenstern
Publicado en: Computer Graphics Forum, Edición 44, 2025, ISSN 0167-7055
Editor: Wiley
DOI: 10.1111/CGF.70078

Next Generation XR Systems—Large Language Models Meet Augmented and Virtual Reality

Autores: Muhamamd Zeshan Afzal, SK Aziz Ali, Didier Stricker, Peter Eisert, Anna Hilsmann, Daniel Perez-Marcos, Marco Bianchi, Sonia Crottaz-Herbette, Roberto De Ioris, Eleni Mangina, Mirco Sanguineti, Ander Salaberria, Oier Lopez de Lacalle, Aitor García-Pablos, Montse Cuadros
Publicado en: IEEE Computer Graphics and Applications, Edición 45, 2025, ISSN 0272-1716
Editor: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/MCG.2025.3548554