EUREKA Xecs TASTI Application-tailored Synthetic Image Generation
| Reference number | |
| Coordinator | Mentice AB |
| Funding from Vinnova | SEK 3 000 000 |
| Project duration | January 2023 - December 2025 |
| Status | Completed |
| Venture | Eureka cluster co-funding |
| Call | EUREKA Xecs Call 2022 - International collaborative projects in electronic components and systems for sustainable digital transformation - national application |
Important results from the project
The goals of the project as a whole were to create methods for synthetic image generation, for methods to assess the quality of such images, and to find new and better applications for those synthetic images. The improvements of our simulation platform that we were able to achieve through this project, improving several of the important realism parameters, met our expectations. It also made our connection with the partners in the this project stronger.
Expected long term effects
Significant avancements in AI has been observed, that further has confirmed the validity of this project. The application of AI algorithms can be seen in more and more products, emergingly endovascular robotic surgery. Large investments are expected to be done in exactly this space the next 5 years (for example by the US government, ARPA-H AIR program), and we think that Mentice has a great positions to be a supplier of training data, and also in the control software for such robots.
Approach and implementation
The work was divided into several work packages, with Mentice mainly contributing to Work Package 3 on synthetic image generation and assessment. Internally, three software teams focused on physics, rendering, and application development, coordinated by a TASTI project manager and supported by R&D management. Externally, Mentice led Work Package 3 within the TASTI consortium, coordinating progress through regular meetings and strengthening collaboration with academic and industrial partners.