Open and reusable components repository
This page provides a living list of the technical outputs of EU research projects funded under the Horizon Europe programme in the Virtual Worlds domain.
Each of the output is linked to its originating project, as listed in the OPENVERSE Collective Intelligence. The content is organised by type of asset.
Disclaimer and intellectual property acknowledgement: all content advertised in this page has been created by third parties, the OPENVERSE consortium is not responsible for incorrect information. The original creator of the content is the sole responsible for the content of the assets. The mere listing of the outputs on this page by is no means to be intended as an endorsement by the OPENVERSE consortium. The intellectual property of the content published in this page belongs to the rightful owners. This page is to be regarded as a pragmatic entry point.
| Project | Title | Type of Asset | Link / DOI | Description |
|---|---|---|---|---|
| LUMINOUS | Text2CAD | AI Model | https://luminous-horizon.eu/index.php/blogs/introducing-text2cad-revolutionizing-cad-generation-from-text-prompts-for-next-gen-xr-in-luminous/ | A generative model capable of producing sequential CAD designs from text prompts. |
| Meetween | Speech LMM open release - V1 | AI Model | https://huggingface.co/meetween/Llama-speechlmm-1.0-l | Open release of the Speech Large Multimodal Model (SpeechLMM) created by the project. |
| XTREME | Multi-Flow: Multi-View-Enriched Normalizing Flows | AI Model | https://doi.org/10.48550/ARXIV.2504.03306 | Advanced deep learning framework created for industrial anomaly detection. |
| LUMINOUS | MARVEL-40M+ | AI Model / Framework | https://doi.org/10.1109/CVPR52734.2025.00759 | A multi-level visual elaboration framework designed for high-fidelity text-to-3D content creation. |
| CORTEX2 | Dynamic Cost Volumes with Scalable Transformer Architecture for Optical Flow | AI Model / Software | https://doi.org/10.5281/zenodo.8253051 | A neural network architecture and software framework for accurate optical flow estimation. |
| SHARESPACE | CT-DQN: Control-Tutored Deep Reinforcement Learning | AI Model / Software | https://doi.org/10.48550/arXiv.2212.01343 | Code base and model architecture for a control-tutored deep reinforcement learning methodology. |
| CORTEX2 | Uni-SLAM | AI Model / Software | https://cortex2.eu/2025/11/29/cortex2-publication-uni-slam-uncertainty-aware-neural-implicit-slam-for-real-time-dense-indoor-scene-reconstruction/ | An uncertainty-aware neural implicit SLAM model developed for real-time dense indoor scene reconstruction. |
| EXPERIENCE | 4Ward | Algorithm / Software | https://doi.org/10.1016/j.neucom.2023.127058 | A relayering strategy designed for the efficient training of arbitrarily complex directed acyclic graphs. |
| XReco | XR and Media Transformation APIs and Authoring Tools | APIs / Tools | https://xreco.eu/deliverables/#toc_D41_XR_and_Media_Transformation_Services_API_and | APIs integrating vertical technologies for XR media transformation and content creation. |
| XR2Learn | V-Lab | Application Framework | https://doi.org/10.1145/3565066.3608246 | A VR educational application framework acting as a beacon application for immersive learning. |
| XR2Learn | INTERACT | Authoring Tool | https://doi.org/10.1145/3565066.3608250 | An authoring tool facilitating the creation of human-centric interaction with 3D objects in VR. |
| EO4EU | European pollen reanalysis, 1980-2022, for alder, birch, and olive, v.1.1 | Dataset | https://doi.org/10.1038/S41597-024-03686-2 | An extensive dataset providing pollen reanalysis (alder, birch, and olive) across Europe. |
| VERGE | Space and Time User Distribution in a University Campus | Dataset | https://doi.org/10.1016/J.COMNET.2024.110329 | Measurement dataset containing spatiotemporal distributions of users. |
| CORTEX2 | X-RiSAWOZ | Dataset | https://doi.org/10.48550/arxiv.2306.17674 | High-quality end-to-end multilingual dialogue datasets accompanied by few-shot agents. |
| DIDYMOS-XR | Dataset for Learning Scene Semantics from Vehicle-centric Data for City-scale Digital Twins | Dataset | https://ieeexplore.ieee.org/document/10859207 | Data utilized for learning scene semantics intended for city-scale digital twins. |
| DIDYMOS-XR | ADAPT JR-Sim2Real dataset | Dataset | https://zenodo.org/records/12805642 | Dataset associated with domain transfer for instance segmentations for AR scenes. |
| e-DIPLOMA | European remote e-learning ecosystem survey data | Dataset | https://doi.org/10.5281/ZENODO.10432816 | Survey data detailing the remote e-learning ecosystem across Europe. |
| SHARESPACE | Deep Space Starter Kit | Software | https://github.com/ArsElectronicaFuturelab/UE-DeepSpace-Starter | The Deep Space Starter Kit is an Unreal Engine template includes all configurations to quickly start a new project for this specific space. This plug-in is compatible with Unreal Engine 5.7. |
| CORTEX2 | FREDSum | Dataset | https://arxiv.org/abs/2312.04843 | A dialogue summarization corpus specifically designed around French political debates. |
| GuestXR | Motivational Interviewing Transcripts Annotated | Dataset | https://doi.org/10.5281/zenodo.12792623 | Annotated transcripts used for training AI-generated patient simulations. |
| GuestXR | MB-RIRs: a Synthetic Room Impulse Response Dataset | Dataset | https://doi.org/10.48550/arxiv.2507.09750 | Synthetic room impulse responses featuring frequency-dependent absorption coefficients. |
| Meetween | Mumospee open release - V1 | Dataset | https://huggingface.co/datasets/meetween/mumospee | One of the largest open multimodal datasets created to train the SpeechLMM. |
| Meetween | MOSEL | Dataset | https://doi.org/10.18653/V1/2024.EMNLP-MAIN.771 | 950,000 hours of speech data utilized for open-source speech foundation model training on EU languages. |
| Meetween | NUTSHELL | Dataset | https://doi.org/10.18653/V1/2025.IWSLT-1.2 | A dataset built specifically for abstract generation from scientific talks. |
| SONICOM | The SONICOM HRTF Dataset | Dataset | https://doi.org/10.17743/jaes.2022.0066 | Dataset of Head-Related Transfer Functions for artificial intelligence-driven immersive audio. |
| SONICOM | PAN-AR | Dataset | https://doi.org/10.1145/3678299.3678332 | A multimodal dataset featuring higher-order ambisonics room impulse responses and spherical pictures. |
| SUN | Simulation of Heuristics for AGV Task Sequencing | Dataset | https://doi.org/10.3390/MATH12020271 | Replication data utilizing dynamic queues and resource sharing. |
| SUN | Knee Rehabilitation Dataset | Dataset | https://doi.org/10.1038/S41597-025-04963-4 | A specialized dataset of knee rehabilitation exercises for postural assessment utilizing wearable devices. |
| TransMIXR | UVG-CWI-DQPC: Dual-Quality Point Cloud Dataset | Dataset | https://doi.org/10.1145/3746027.3758263 | Point cloud dataset optimized for volumetric video applications. |
| TransMIXR | ComPEQ-MR | Dataset | https://doi.org/10.1145/3625468.3652182 | A compressed point cloud dataset featuring eye tracking and quality assessment in mixed reality. |
| SUN | MC-GTA | Dataset / Benchmark | https://doi.org/10.5281/zenodo.8335396 | A synthetic benchmark dataset aimed at advancing multi-camera vehicle tracking capabilities. |
| TransMIXR | TSalV360: Text-driven Saliency Detection | Dataset / Method | https://doi.org/10.5281/ZENODO.17649129 | Method and dataset tailored for saliency detection within 360-degree videos. |
| XReco | Textual Video Content Dataset | Dataset / Metric | https://doi.org/10.1145/3746027.3758224 | A dataset and corresponding metric created specifically for textual video content description. |
| Meetween | FAMA | Foundation Model | https://doi.org/10.48550/ARXIV.2505.22759 | The first large-scale open-science speech foundation model for Italian and English. |
| AI4WORK | Core concepts for mid- and domain-level ontology development | Ontology / Framework | https://doi.org/10.5281/ZENODO.13148630 | Ontologies required to facilitate explainable-AI-readiness of data and models. |
| XReco | vitrivr-engine | Open-Source Engine | https://doi.org/10.1145/3746027.3756874 | An open-source multimedia retrieval engine for content and similarity searches. |
| MAX-R | Data Hubs / XRDataHub | Open-Source Software | https://github.com/FilmakademieRnd/DataHub | Open-source software associated with XRDataHub, AnimHost, and browser-based XR tools. |
| SONICOM | NumCalc | Open-Source Software | https://doi.org/10.1016/j.enganabound.2024.01.008 | An open-source Boundary Element Method (BEM) code for solving acoustic scattering problems. |
| TransMIXR | VR2Gather | Open-Source System | https://doi.org/10.1145/3664647.3685515 | A collaborative social VR system open-sourced for adaptive multi-party real-time communication. |
| GuestXR | Inceptor | Open-Source Tool | https://doi.org/10.1109/vrw58643.2023.00102 | An open-source tool developed for the automated creation of 3D social scenarios in virtual environments. |
| XR4Human | Online Rating Repository | Repository | https://doi.org/10.5281/ZENODO.17896488 | Digital repository functioning as a rating and evaluation tool for human-centered XR frameworks. |
| GuestXR | Topo-Speech | Sensory System | https://doi.org/10.3389/fnhum.2022.1058093 | A sensory substitution system conveying spatial information to blind and vision-impaired individuals. |
| POPULAR | AR Eyewear Simulation Tool | Simulation Tool | https://doi.org/10.1117/12.3042612 | A software simulation tool explicitly developed for holographic-based augmented reality eyewear. |
| SONICOM | Auditory modelling toolbox (AMT) | Software | https://ecosystem.sonicom.eu/tools/1 | Toolbox to facilitate reproducible research in auditory modeling. |
| DIDYMOS-XR | MGSO | Software / Algorithm | https://doi.org/10.48550/ARXIV.2409.13055 | A monocular real-time photometric SLAM algorithm utilizing efficient 3D Gaussian Splatting. |
| PRESENCE | LiveSkeleton | Software / Algorithm | https://doi.org/10.1109/ISM63611.2024.00054 | A system providing high-quality real-time human tracking and pose estimation. |
| SPIRIT | GreenWise | Software / Algorithm | https://doi.org/10.1145/3773274.3774275 | An intelligent application migration framework for containerized machine learning services. |
| CyberSecDome | REACT: Autonomous intrusion response system | Software / Framework | https://doi.org/10.48550/arxiv.2401.04792 | Autonomous intrusion response system tailored for intelligent vehicles. |
| CyberSecDome | Shells Bells | Software / Framework | https://doi.org/10.5281/zenodo.14807181 | A cyber-physical anomaly detection framework designed for data centers. |
| DIDYMOS-XR | HINT-3D | Software / Framework | https://doi.org/10.5281/ZENODO.18491843 | A human-in-the-loop interactive test-time adaptation framework for 3D segmentation. |
| DIDYMOS-XR | Visual localization using implicit representations | Software / Model | https://doi.org/10.5281/ZENODO.18468790 | Software for visual localization utilizing implicit representations and particle filtering-based pose refinement. |
| e-DIPLOMA | e-DIPLOMA Platform Software | Software / Platform | https://doi.org/10.5281/ZENODO.14534383 | A complex package of cooperating software modules for the e-DIPLOMA learning ecosystem. |
| CyberSecDome | PTPsec | Software Code | https://doi.org/10.5281/ZENODO.14806692 | A security tool designed to protect the Precision Time Protocol against time delay attacks using cyclic path asymmetry analysis. |
| MAX-R | EDM-Research/UE-LASAA | Software Code | https://doi.org/10.5281/zenodo.15517094 | Published code base developed to support the project's XR media pipelines. |
| XR2Learn | XR2Learn platform | Online tool | https://xr2learn.eu/platform/ | The software code structure of the XR marketplace, including the on-demand components and IPR tools. |
| VERGE | Edge4AI | Software Framework | https://doi.org/10.5281/ZENODO.15878533 | A framework enabling intelligent edge automation and AI lifecycle management for Beyond 5G networks. |
| TrustChain | Decentralized Management of Federated Cloud and Edge Providers | Software Framework | https://doi.org/10.5281/ZENODO.10785252 | A management framework for the efficient and budget-balanced handling of federated cloud and edge platforms. |
| EXPERIENCE | Virtual Experience Toolkit | Software Framework | https://doi.org/10.3390/s24123837 | An end-to-end automated 3D scene virtualization framework using computer vision techniques. |
| NANOVR | Martinize2 and Vermouth | Software Framework | https://doi.org/10.48550/arxiv.2212.01191 | A unified framework utilized for molecular topology generation. |
| SONICOM | Frambi | Software Framework | https://doi.org/10.61782/fa.2023.0494 | A flexible software framework tailored for auditory modeling based on Bayesian inference. |
| TrustChain | SURE: Privacy and Utility Assessment Library | Software Library | https://doi.org/10.5281/ZENODO.13843053 | A new library designed to assess privacy and utility for synthetic data. |
| SUN | Ubervvald | Software Library | https://doi.org/10.1007/978-981-96-5887-9_14 | An advanced object detection library created to optimize complex Convolutional Neural Networks (CNNs). |
| NANOVR | NanoVer Server | Software Package | https://doi.org/10.21105/joss.08118 | A Python package for serving real-time multi-user interactive molecular dynamics in VR. |
| MASTER | IMETA | Software Tool | https://doi.org/10.1145/3581754.3584125 | An interactive mobile eye-tracking annotation method for semi-automatic fixation-to-AOI mapping. |
| TransMIXR | TangibleMRCreate | Software Tool | https://doi.org/10.2312/EGVE.20231339 | An intuitive authoring tool created to facilitate the development of mixed reality content. |
| HEAT | EmoLoop | System / Software | https://doi.org/10.1109/IS264627.2025.11284604 | A bi-directional system designed for emotion-driven interaction between remote audiences and performers. |
| SPIRIT | STEP-MR | Testing Platform | https://athena.itec.aau.at/2025/11/step-mr-a-subjective-testing-and-eye-tracking-platform-for-dynamic-point-clouds-in-mixed-reality/ | A subjective testing and eye-tracking platform built specifically for dynamic point clouds in mixed reality. |
| PRESENCE | Flexible toolkit for real-time action recognition | Toolkit / Software | https://doi.org/10.5281/ZENODO.15974094 | A flexible, reusable toolkit for the real-time action recognition of virtual humans in XR/AR environments. |
| e-DIPLOMA | Photogrammetry workflow for low-polygon 3D models | Workflow / Tool | https://repositori.uji.es/bitstreams/578c3673-2fd3-40e8-aac6-483cb08eacf8/download (PDF File) | A reusable workflow relying on free software to obtain low-polygon 3D models. |
| SHARESPACE | pharus | Plug-in | https://github.com/ArsElectronicaFuturelab/UE-DeepSpace-PharusLasertracking | The pharus tracking system is developed by researcher and artist Otto Naderer from the Ars Electronica Futurelab. This tracking system allows for the locations of objects, people, or groups to be tracked on the Deep Space floor. |
| SHARESPACE | Deep Sync Infrastructure | Plug-in | https://github.com/ArsElectronicaFuturelab/UE-DeepSpace-DeepSync https://github.com/ArsElectronicaFuturelab/DeepSync-Wearable-Server https://github.com/ArsElectronicaFuturelab/DeepSync-Wearable-Firmware | The Deep Sync Infrastructure brings biodata to the co-immersive Deep Space 8K. It includes the development of custom-made wearables and an Unreal Engine plug-in. |
| SHARESPACE | Cognitive Architectures | Plug-ins | https://sharespace.eu/cognitive-architectures/ | Within SHARESPACE, cognitive architectures were designed, developed, and validated by SHARESPACE partner CRdC to drive the movement of virtual characters with different levels of autonomization. |
| SHARESPACE | Pixel Streaming Service | Plug-in | https://github.com/ALE-Rainbow/sharespace-pixel-streaming-infrastructure | WebRTC enables direct peer-to-peer audio connections that avoid the mixing delays inherent in centralized voice systems. A mesh network architecture allows multiple P2P connections between emitters and receivers, minimizing latency while maintaining audio quality. |
| SHARESPACE | Web Client-Server Bundle | Plug-in | https://github.com/ALE-Rainbow/sharespace-pixel-streaming-cpp-service | The project delivered a web client-server bundle that could be hosted either locally or in ALE cloud with connectors for direct connection with XR applications. |
| SHARESPACE | Avatar Replication in Shared Environments | Plug-in | https://github.com/CYENS/virtual-share-space | A unified multi-user platform was developed in Unreal Engine 5 by the team of Cyens, allowing distributed clients to connect and interact within shared virtual environments. |