View publication
| Title | Towards Automatizing Crowdsourcing for Virtual Museums |
| Authors | Felipe Escarate, Nelson Baloian, José A. Pino |
| Publication date | 2025 |
| Abstract | This study explores the possibilities of automazing the process of crowdsourcing contributions to virtual museums by utilizing advanced 3D modeling techniques. The research investigates how far the process of integrating user-submitted content -- such as videos, images and text -- into virtual museum environments can be automated. A web-based platform was developed to facilitate artifact uploads, which are processed using Gaussian splatting to generate high-quality 3D models. One key result reveals that the process can be almost fully automated, with only a user-friendly final model editing phase required. This editing phase not only ensures quality control but also allows contributors to refine the final output, enhancing the accuracy and consistency of the artifacts integrated into the virtual museum. The backend system, built with REST APIs and integrated with Unity, ensures seamless communication between the user interface and model generation pipeline, enabling efficient artifact visualization. Gaussian Splatting produces smoother, more realistic models compared to traditional techniques, even when handling contributions from non-expert users. This research highlights the potential of automating the entire digitization workflow while maintaining quality through collaborative editing. Future work will explore the use of augmented reality and real-time rendering technologies to further enhance user engagement |
| Pages | 2184-2189 |
| Conference name | IEEE International Conference on Computer Supported Collaborative Work in Design |
| Publisher | IEEE Computer Society Press (Los Alamitos, CA, USA) |
| Reference URL |
|