{"links":{"self":"http://dataportal.arc.gov.au/NCGP/API/grants/FT250100448"},"data":{"type":"grant-details","id":"FT250100448","attributes":{"code":"FT250100448","administering-organisation":"Murdoch University","announcement-administering-organisation":"Murdoch University","scheme-name":"ARC Future Fellowships","grant-status":"Active","funding-commencement-year":2025,"years-funded":4,"project-start-date":"2026-02-01","anticipated-end-date":"2030-01-31","grant-summary":"Rethinking 4D Shape Statistics via Neural Functional Representations. This project will develop novel mathematical tools and machine learning algorithms for the statistical modelling and analysis of how biological objects develop their 3D shape, grow and deform as they interact with their environment. It will generate new knowledge on how to mathematically model the 3D geometry, deformations and growth using a novel generation of neural networks that are physically motivated, compact and fast to train. These are crucial for understanding developmental processes, natural growth and disease progression in biological objects. Expected outcomes include innovative techniques and computational tools that operate directly on RGB images and videos, with substantial benefits to biology, health and computer vision. ","funding-current":1304440.00,"funding-at-announcement":1276884,"investigators-current":[{"title":"Prof","firstName":"Hamid","familyName":"Laga","roleName":"Future Fellowship","roleCode":"FT","isFellowship":true,"orcidIdentifier":"0000-0002-4758-7510 "}],"investigators-at-announcement":[{"title":"Prof","firstName":"Hamid","familyName":"Laga","roleName":"Future Fellowship","roleCode":"FT","isFellowship":true,"orcidIdentifier":"0000-0002-4758-7510 "}],"organisations-current":[{"organisationName":"Murdoch University","roleName":"Administering Organisation","state":"WA"}],"organisations-at-announcement":[{"organisationName":"Murdoch University","roleName":"Administering Organisation","state":"WA"}],"field-of-research":[{"isPrimary":true,"code":"4603","name":"Computer Vision and Multimedia Computation","type":"FOR20"},{"isPrimary":false,"code":"460304","name":"Computer Vision","type":"FOR20"},{"isPrimary":false,"code":"461103","name":"Deep Learning","type":"FOR20"}],"socio-economic-objective":[{"code":"220403","name":"Artificial Intelligence","type":"SEO20"},{"code":"220501","name":"Animation, Video Games and Computer Generated Imagery Services","type":"SEO20"}],"international-collaboration":["England","United States of America"],"lief-register":[],"achievement-summary":null,"national-interest-test-statement":"Shape is an important property of objects, from bones, blood vessels and neuronal structures to human bodies and plants. It is intimately related to their biological function, biomechanics, the way they interact with their environment and their evolutionary adaptation. Shape also deforms over time, either normally or abnormally due to disease progression. This project will develop novel algorithms for mathematically modelling how 3D objects develop their shape and how it evolves and grow as they age and interact with their surroundings. This is important for many applications, from biology and health to augmented reality. However, traditional techniques require 3D and 4D data which are expensive, time-consuming and often not feasible to acquire when dealing with non-cooperative objects. This project will develop innovative solutions, combining tools from differential geometry, physics and deep learning, to overcome the limitations of traditional techniques by operating directly on images and videos, which are widely available and can be easily captured. This research will economically benefit many sectors from biology, health and environment to entertainment and manufacturing. By sharing our findings in international conferences, industry forums and public media, and making the algorithms publicly available, this project will enhance Australia’s reputation as a leading centre for research in this area and accelerate the translation and adoption of the project’s findings."}}}