3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environmen ....3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environments and open up new possibilities for applications in fields such as virtual reality, architecture, and city planning. The proposed 3D diffusion models will also enhance the accuracy of computer vision tasks related to 3D scene understanding, such as object detection, tracking, and semantic segmentation.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100477
Funder
Australian Research Council
Funding Amount
$421,554.00
Summary
Advancing Human Perception: Countering Evolving Malicious Fake Visual Data. The aim of this project is to provide new effective and generalisable deepfake detection methods for automatically detecting maliciously manipulated visual data generated by misused artificial intelligence (AI) techniques. It will present innovative computer vision and image processing knowledge and techniques, enabling the developed methods to advance human perception in recognising fake data, enhance cybersecurity, and ....Advancing Human Perception: Countering Evolving Malicious Fake Visual Data. The aim of this project is to provide new effective and generalisable deepfake detection methods for automatically detecting maliciously manipulated visual data generated by misused artificial intelligence (AI) techniques. It will present innovative computer vision and image processing knowledge and techniques, enabling the developed methods to advance human perception in recognising fake data, enhance cybersecurity, and protect privacy in AI applications. The anticipated outcomes should provide significant benefits to a wide range of applications, such as providing timely alerts to the media, government organisations, and the industry about misleading fake visual data, and preventing financial crimes on synthetic identity fraud.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100967
Funder
Australian Research Council
Funding Amount
$366,000.00
Summary
Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected o ....Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected outcomes include new paradigms for algorithm design and evaluation, and establishing the problem as a focus of international research. The key practical benefit would be to accelerate the wider deployment of visual perception in applications such as autonomous vehicles, interactive robotics, and video analysis.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101058
Funder
Australian Research Council
Funding Amount
$437,254.00
Summary
Glass-box Deep Machine Perception for Trustworthy Artificial Intelligence. Explainability and Transparency are the key values for development and deployment of Artificial Intelligence (AI) in Australia’s AI Ethics Framework for industry and governments. This project aims to build new tools to make the central technology of AI - deep learning - transparent and explainable. Its expected outputs are novel theory-driven algorithms and unconventional foundational blocks for deep learning that will al ....Glass-box Deep Machine Perception for Trustworthy Artificial Intelligence. Explainability and Transparency are the key values for development and deployment of Artificial Intelligence (AI) in Australia’s AI Ethics Framework for industry and governments. This project aims to build new tools to make the central technology of AI - deep learning - transparent and explainable. Its expected outputs are novel theory-driven algorithms and unconventional foundational blocks for deep learning that will allow humans to clearly interpret the reasoning process of this technology, which is currently not possible. It is expected to significantly advance our knowledge in machine intelligence and perception. Due to their fundamental nature, the project outcomes are likely to benefit industry and scientific frontiers alike.Read moreRead less
A Machine Learning Framework for Concrete Workability Estimation . Concrete is the most used construction material in Australia. The project aims to develop a system to measure the workability of concrete in transit in agitator trucks using advanced machine vision and machine learning, and provide a reliable alternative to the current practice of visually testing concrete workability by certified testers. Concrete that fails to meet workability requirements is one of the most frequent reasons fo ....A Machine Learning Framework for Concrete Workability Estimation . Concrete is the most used construction material in Australia. The project aims to develop a system to measure the workability of concrete in transit in agitator trucks using advanced machine vision and machine learning, and provide a reliable alternative to the current practice of visually testing concrete workability by certified testers. Concrete that fails to meet workability requirements is one of the most frequent reasons for rejection at construction sites, resulting in significant costs, waste, and delays. Multimodal data sources will be used to provide a reliable workability estimate in real time, enabling construction teams to identify and rectify workability issues in transit while continuously monitoring the adjustments effects.Read moreRead less
Shape4D: Modelling the Spatiotemporal Deformation Patterns in 3D Shapes. This research will develop new mathematical methods and algorithms that will enable the use of population-level longitudinal studies to model the spatial and temporal deformation patterns in 3D biological objects. Using novel geometric and deep learning techniques, it will create new methods that will allow the characterization of how the 3D shape of objects deforms with ageing, disease progression and interaction with thei ....Shape4D: Modelling the Spatiotemporal Deformation Patterns in 3D Shapes. This research will develop new mathematical methods and algorithms that will enable the use of population-level longitudinal studies to model the spatial and temporal deformation patterns in 3D biological objects. Using novel geometric and deep learning techniques, it will create new methods that will allow the characterization of how the 3D shape of objects deforms with ageing, disease progression and interaction with their environment, and the simulation of spatiotemporal deformations in anatomical organs. Benefits include a better understanding of growth processes, predictive models of how degenerative diseases progress and a computational framework that will assist in designing proper mitigation and intervention strategies.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100149
Funder
Australian Research Council
Funding Amount
$462,044.00
Summary
Adaptive and Efficient Robot Positioning Through Model and Task Fusion. This project aims to create fit-for-purpose positioning systems that continuously adapt to diverse and changing environments. The project expects to contribute to the knowledge across robotics, computer vision, and neuromorphic computing. Expected outcomes of this project include ground-breaking place recognition techniques that address two fundamental limitations in the state-of-the-art: continuous adaptation, critically im ....Adaptive and Efficient Robot Positioning Through Model and Task Fusion. This project aims to create fit-for-purpose positioning systems that continuously adapt to diverse and changing environments. The project expects to contribute to the knowledge across robotics, computer vision, and neuromorphic computing. Expected outcomes of this project include ground-breaking place recognition techniques that address two fundamental limitations in the state-of-the-art: continuous adaptation, critically important in safety-critical systems, and energy efficiency, critically important in resource-constrained systems. This should provide significant benefits, such as accelerated deployment of mobile robots, drones and augmented reality solutions in manufacturing, defence, healthcare, household, and space.Read moreRead less
Tensor and Hypergraph Methods in Fitting Visual Data. This proposal will put an important class of clustering (extracting data that should fit a geometric model) on a more solid theoretical foundation. This will lead to better understanding of how to certify outcomes, efficiency, reliability etc. The type of clustering under consideration is relevant to many problems in machine learning and computer vision, as well as data mining and a wide variety of other settings.
New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less
Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the ....Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the primary limitations of deep learning and will greatly increase its practical application to a range of industrial, cultural or health settings.Read moreRead less