Colourlab, part of the Department of Computer Science at NTNU Gjøvik, continues to strengthen its position as one of Europe’s leading research environments in visual technology, cultural heritage and medical image analysis.
– These are fantastic results. I am proud and enthusiastic. This clearly demonstrates the value of long-term, high-quality research efforts, says Thomas Tybell, Dean of the Faculty of Information Technology and Electrical Engineering at NTNU.
Exceptional Success in a Highly Competitive EU Programme
In the latest call from the EU’s Marie Sklodowska-Curie Actions (MSCA), Colourlab was awarded four new MSCA projects, three as coordinator and one as partner, as well as two additional EU-funded research and innovation projects. Acting as project coordinator is considered one of the highest recognitions within the EU funding system.
– This is recognition at a very high level and demonstrates the strength of the academic environment at Colourlab. The work not only contributes to world-class research, but also to solutions with significant societal value, says Stephen Dobson, Vice-Rector at NTNU in Gjøvik.
This year’s MSCA call received 1,616 applications from European universities, of which only 141 projects were funded, corresponding to a success rate below nine percent.
NTNU submitted 99 applications, and 12 projects were funded. All three projects awarded with coordinator responsibility were assigned to Colourlab at NTNU in Gjøvik.
Within the most prestigious scheme, MSCA Doctoral Networks, four coordinated projects were awarded to Norwegian institutions. Three of these will be coordinated by Colourlab, an achievement described as unparalleled in the Norwegian context.
– In more than 25 years as the national contact point for MSCA, I have never seen anything like this. Three Doctoral Networks coordinated by the same research group is extremely rare, says Per Magnus Kommandantvold from the Research Council of Norway.
Strong Impact for Research, Education and Society
MSCA projects typically receive €3 to 4 million each, depending on size and number of researchers. Across all funded projects, 60 PhD candidates will be trained, of whom 12 will be employed at NTNU and based at Colourlab in Gjøvik.
According to Professor Marius Pedersen, Deputy Head of Department and one of the project coordinators, the projects will:
- strengthen Colourlab’s research capacity
- enable recruitment of highly qualified PhD candidates
- expand international and industrial collaboration
- increase NTNU’s visibility and leadership in Europe
The research will address challenges within cultural heritage preservation, healthcare diagnostics, industrial production, digital security, and ethical use of AI.
Research Focus Areas
Project start-up is expected in early 2027. The research activities include:
- Advanced imaging and digital twins to monitor and preserve cultural heritage
- Improved medical image analysis for capsule endoscopy, enabling faster and more accurate diagnosis of gastrointestinal diseases
- How the appearance of materials can be measured to support more precise and sustainable manufacturing processes.
- Explainable AI systems to detect deepfakes and combat digital crime
- Ethical, non-invasive age assessment technologies for use at European borders
Overview of the Six EU Projects
WILD-MAIDN:
Human evolution has endowed us with refined visual and cognitive skills, enabling material appearance assessment across diverse conditions and contexts. While the physics of light transport within materials is well understood, the visual mechanisms underlying perceptual equivalence among materials remain largely unexplored, and no reliable metric currently quantifies perceptual differences between them. This gap is a critical barrier to advancing aesthetic product design and manufacturing, particularly with the advent of complex designs featuring visual (color, gloss, translucency, texture) and haptic (softness, roughness) attributes made possible by new manufacturing technologies like multimaterial 3D printing. These innovations facilitate decentralized production, reducing supply chain dependence and energy consumption while enabling high-quality, customized parts, such as aesthetic dental restorations. However, current quality control methods rely on subjective visual inspection, creating variability and limiting reproducibility, especially for products requiring high appearance accuracy. To overcome this, appearance difference metrics are essential for quality control and design adjustments in line with manufacturing constraints (Appearance Gamut Mapping). Furthermore, generative AI (genAI) models in automatic product design require differentiable loss functions that capture human perception of material appearance. The WILD MAIDN project aims to establish foundational metrics for appearance difference and equivalence, advancing visual perception science and providing tools for automated, perceptually-driven design and production that can ultimately support future genAI applications.
UNCHANGE:
Cultural Heritage (CH) objects change over time due to environmental factors, material aging, and past human actions. These changes often invisible until they become irreversible and are difficult to measure, interpret, and predict. As digital technologies, imaging, and data science increasingly influence conservation practices, there is a growing need for researchers and professionals skilled in linking material knowledge, conservation science, advanced imaging, and artificial intelligence.
UNCHANGE addresses this need by exploring how and why CH materials change, connecting the physical and chemical causes of deterioration to their visible and invisible effects. The project will develop non-invasive imaging methods, mechanistic models, and computational tools to document, analyze, and forecast changes. These innovations will help create heritage digital twins of heritage objects, enabling better conservation decisions and new ways to visualize their past, present, and future states. As a Doctoral Network, UNCHANGE will train a new generation of researchers capable of working across conservation science, materials science, imaging physics, and AI. Through close collaboration with museums, heritage institutions, and scientific partners, the project will test its methods on representative case studies and promote the digital transformation of the sector. By improving understanding, monitoring, and communication of changes in CH objects, UNCHANGE aims to support more resilient and evidence-based strategies for their long-term preservation.
CAPTURE:
The CAPTURE project focuses on improving wireless capsule endoscopy for improved diagnosis, monitoring and treatment of patients. There have been increases in the incidence of most gastrointestinal disorders in Europe, which has major implications for future healthcare services. The incidence and prevalence of many gastrointestinal disorders are highest among older people, and with an ageing European population, this will lead to an increased burden on healthcare across Europe. We will have special attention to IBDs, as this is increasing in occurrence in Europe. Several reports have highlighted a lack in both the content and quality of education and training in gastroenterology in Europe.
The CAPTURE project will advance WCE to improve image-based diagnosis, monitoring, and treatment of patients. CAPTURE will lead to innovative techniques and tools to reduce the workload of medical professionals, improve the imaging capabilities of WCE resulting in improved diagnosis, and tools and knowledge to train a new generation of medical professionals and researchers. We will focus on the specific group of IBD with the increasing prevalence in Europe. This goal will be achieved by training 15 doctoral candidates in key aspects of WCE, ranging from technical image-related aspects to clinical aspects, all with an interdisciplinary approach.
GLASS-CARE:
Glass-Care addresses the need to safeguard Europe’s stained-glass heritage, which is rapidly deteriorating due to pollution, climate fluctuations and the decline of traditional restoration skills. These iconic artworks, central to European cultural identity, remain insufficiently documented and increasingly vulnerable. Current conservation approaches often depend on destructive sampling and lack standardised, sustainable methods. Glass-Care goes beyond the state of the art by integrating portable spectroscopy, advanced imaging, green chemistry and digital infrastructures. The project introduces innovative technologies, photoacoustics, ptychographic microscopy and multimodal tomography, together with eco-friendly cleaning and reconstruction protocols, predictive deterioration models and a digital twin stained-glass window model. These advances will enable real-time condition assessment, long-term monitoring and environmentally responsible conservation strategies. Through an ambitious MSCA Doctoral Network, Glass-Care trains 15 doctoral candidates in an international, interdisciplinary and intersectoral environment. Fellows will combine hands-on research with thematic schools and transferable-skills development, gaining expertise in cutting-edge analytical techniques, sustainable materials and advanced data processing. They will be equipped to become future leaders in heritage science and conservation. Glass-Care’s impact is far-reaching: it will deliver 15 end-user protocols, 4 demonstrator set-ups, 2 reference databases and 3 digital infrastructures to ensure uptake by museums, conservators and educators. By aligning technological innovation with sustainability and education, the project strengthens Europe’s leadership in cultural-heritage preservation, supports the Green Deal and multiple SDGs. Its outcomes will enhance Europe’s capacity to protect stained-glass windows and ensure that conservation practice evolves with environmental pressures and societal needs.
DEFORM:
DEFORM addresses the urgent need for robust, explainable AI forensic tools to counter the growing threat of Deepfakes, AI-generated or manipulated audio, video, and images that challenge current forensic tools. The project will deliver a modular, practitioner-driven AI framework with multi-level explainability for multimodal Deepfake detection and source tracing, validated (TRL5) and demonstrated (TRL6) in 2 operational forensic environments. DEFORM’s innovative approach leverages emerging Foundation Representation Models and few-shot learning for robust and multilevel explainable AI (xAI) to ensure adaptability to new manipulation techniques and transparency for diverse stakeholders, including investigators, forensic examiners, legal professionals, and lay audiences. The consortium unites leading scientific, technical, legal, and practitioner partners from six European countries, including police authorities and forensic institutes, to co-design, validate, and demonstrate solutions aligned with EU legal, ethical, and forensic standards. By twinning expert research partners in scientific, legal and ethical part from partner countries with practitioners from respective countries, DEFORM outputs include validated detection and source tracing modules for image, audio, and video; human-centred xAI explanations; annotated Deepfake datasets; and open-source forensic tools for wide adoption.
DEFORM’s impact pathway ensures improved reliability and usability for modern forensic analysis using new and emerging technology. This will enhance the capacity for law enforcement to fight against crimes in digital area and strengthen public trust. DEFORM’s innovative training curricula will bridge the gap between research and operational practice. Also, stakeholder engagement will foster wide adoption and contribute to a strong and independent EU AI continent.
ELESSAR:
At EU external borders, an increasing number of individuals arrive without valid identity documents, creating uncertainty regarding their exact age. In many instances, there is reasonable doubt about their declared age; whether they present themselves as minors but may be adults, claim to be adults but are suspected to be minors, or are recognised as minors yet believed to be of a different age than stated. The ELESSAR project will design, develop, validate, and demonstrate a rights-preserving, interoperable age-assessment capability for EU border contexts that is (a) non-invasive-first through AI-based multi-modal age assessment based on face, ear, palm and vein characteristics and accompanied by structured interviews and contextual indicators, (b) science-based and uncertainty-aware connected with clear confidence levels and calibrated AI estimation as documented evidence, (c) governed by strong safeguards including guardian/legal representative, informed consent, proportionality, audit trails, gender-sensitive procedures, and (d) interoperable with border IT and future DTC ecosystems. Co-creation with border guards, human rights advocates, and legal/ethics experts will provide a holistic foundation for the development of an age-assessment framework that is operationally practical and firmly grounded in fundamental rights. ELESSAR will establish a harmonised, transparent, and evidence-based approach that enhances the protection of minors and the credibility of border procedures, while reducing legal disputes, accelerating case handling, and reinforcing institutional trust across the EU. Ultimately, it aspires to set a new European benchmark for ethical, AI-assisted age assessment, informing both future policy and operational practice at the EU external borders.