Learned Exascale Computational Imaging (LEXCI)
Lead Research Organisation:
Heriot-Watt University
Department Name: S of Mathematical and Computer Sciences
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Publications
Klatzer T
(2024)
Accelerated Bayesian Imaging by Relaxed Proximal-Point Langevin Sampling
in SIAM Journal on Imaging Sciences
Laumont R
(2022)
Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
in SIAM Journal on Imaging Sciences
Laumont R
(2023)
On Maximum a Posteriori Estimation with Plug & Play Priors and Stochastic Gradient Descent
in Journal of Mathematical Imaging and Vision
| Description | Learned Quantitative Stochastic Imaging |
| Amount | ÂŁ1,506,530 (GBP) |
| Funding ID | EP/Z534481/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 12/2024 |
| End | 12/2029 |
| Title | IMLA |
| Description | The implicit Langevin algorithm (IMLA) is a Markov chain Monte Carlo sampler designed for performing Bayesian inference with machine learning image priors that are log-concave. The algorithm outperforms previous algorithms for this task in terms of computational complexity and affords users with detailed theoretical accuracy guarantees. In addition, IMLA automatically takes into account constraints in the solution space, which are a key feature of low-photon imaging problems. Moreover, IMLA self-calibrates its internal algorithm parameters, and is thus significantly easier to deploy than its competitors. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | We have been actively disseminating IMLA to potential end-users. A biological imaging group in Genoa (Italy), is currently considering applying IMLA to image super-resolution tasks in fluorescent microscopy of single molecule images. |
| URL | https://epubs.siam.org/doi/full/10.1137/23M1594832 |
| Title | PnP-ULA |
| Description | The Plug-and-Play unadjusted Langevin algorithm is a Markov chain Monte Carlo sampler designed for performing Bayesian inference with priors that are represented by an image denoising operator, which is typically encoded by a neural network that has been trained with application-specific data. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2022 |
| Provided To Others? | Yes |
| Impact | PnP-ULA has been successfully applied to problems related to image recovery and uncertainty quantification in a range of imaging inverse problems involving synthetic data. Its application to real problems in computer tomography is currently under investigation. |
| URL | https://doi.org/10.1137/21M1406349 |
| Title | Proximal Nested Sampling |
| Description | Proximal Nested Sampling is a stochastic algorithm designed for computing the marginal likelihood of high-dimensional Bayesian models with an underlying convex geometry. It is based on the Moreau-Yoshida regularised unadjusted Langevin algorithm and it is useful for performing Bayesian model selection directly from observed data, without the need for ground truth data. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2022 |
| Provided To Others? | Yes |
| Impact | Proximal Nested Sampling has been successfully applied to Bayesian model selection in imaging inverse problems involving synthetic data. Its application to real problems in interferometric imaging is currently under investigation. |
| URL | https://link.springer.com/article/10.1007/s11222-022-10152-9 |
| Description | Alain Durmus and Valentin De Bortoli |
| Organisation | École Normale Supérieure de Cachan |
| Country | France |
| Sector | Academic/University |
| PI Contribution | We have led the development of the new technique to adjust the parameters of the mathematical equations underpinning the image enhancement algorithms, as well as the specific applications to imaging that we have studied so far in this project. |
| Collaborator Contribution | Alain Durmus and Valentin De Bortoli have led the theoretical analysis of the new technique, particularly the convergence guarantees under easily verifiable conditions. |
| Impact | This is a multi-disciplinary collaboration at the interface of computational imaging engineering, probability theory, computational statistics, and applied analysis. |
| Start Year | 2017 |
| Description | Julian Tachella (ENS Lyon) |
| Organisation | École normale supérieure de Lyon (ENS Lyon) |
| Country | France |
| Sector | Academic/University |
| PI Contribution | We have co-created a new unsupervised statistical machine learning method that is able to quantify the uncertainty in the solution of an imaging problem directly from measurements, by leveraging symmetries and invariances in the problem, without the need for ground truth data. |
| Collaborator Contribution | Co-creation of the method and implementation of algorithms and experiments |
| Impact | https://arxiv.org/pdf/2310.11838.pdf (accepted for publication in AISTATS 2024). |
| Start Year | 2022 |
| Description | Julie Delon and Andres Almansa |
| Organisation | University of Paris - Descartes |
| Country | France |
| Sector | Academic/University |
| PI Contribution | We have led the development of the new Bayesian AI techniques for imaging problems where the prior knowledge is available in the form of a set of training examples. |
| Collaborator Contribution | Julie Delon and Andres Almansa have led the machine learning aspects of the work and the algorithmic implementation of the proposed techniques. |
| Impact | This is a multi-disciplinary collaboration at the interface of imaging sciences, applied analysis, machine learning, probability theory and mathematical statistics. |
| Start Year | 2019 |
| Title | Equivariant bootstrapping for UQ in Imaging |
| Description | The equivariant bootstrap algorithm is a scalable and intuitive resampling procedure which produces well-calibrated uncertainty regions for linear imaging problem and any reconstruction network (i.e., trained in a supervised or self-supervised manner). The method outperforms other state-of-the-art strategies in terms of accuracy and computational speed. |
| Type Of Technology | Software |
| Year Produced | 2024 |
| Open Source License? | Yes |
| Impact | No impact yet |
| URL | https://arxiv.org/pdf/2310.11838.pdf |
| Description | Invited tutorial at the IEEE International Conference on Image Processing, Bordeaux, Oct. 2022 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The IEEE International Conference on Image Processing is the main global conference on image processing engineering. It is attended by over 1,000 people and has a strong presence from industry. I delivered a 3-hour tutorial masterclass at the conference on the topic of this project. I was subsequently contacted by several engineering groups who are interested in adopting the tools and techniques that I presented at the conference. Two of these groups are currently working on incorporating these tools and techniques into open-source free software libraries that they develop and make available to the image-processing engineering community. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://2022.ieeeicip.org/ |
| Description | Public Lecture (ICMS) |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Public/other audiences |
| Results and Impact | I delivered a public lecture on bias in AI-based computational imaging technology, focusing on the paradox that while bias can have serious negative consequences (illustrated through examples related to discrimination of minority groups), bias it is also an essential ingredient to construct reliable computational imaging methods, as otherwise it would be impossible to separate signal from noise and deliver accurate images. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Stakeholder 3-day workshop |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The 3-day workshop Interfacing Bayesian Statistics, Machine Learning, Applied Analysis, and Blind and Semi-Blind Imaging Inverse Problems" focused on the Bayesian statistics, machine learning, and applied analysis frameworks for imaging inverse problems that are blind or semi-blind. The event brought together industrialists, students, world-leading experts and rising early career researchers to discuss recent developments in the fields as well as open challenges, with a focus on co-creation and on fostering synergies to pursue ideas that develop at the fertile interface where the three frameworks meet. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://www.icms.org.uk/workshops/2023/interfacing-bayesian-statistics-machine-learning-applied-anal... |
| Description | Training event on modern Bayesian imaging techniques for postgraduate research students and industrial researchers |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | Three-day training event, mainly aimed at postgraduate students and industry researchers, on state-of-the-art Bayesian imaging techniques with a focus on uncertainty quantification. Co-organised with Danish Technical University, at ICMS Edinburgh. |
| Year(s) Of Engagement Activity | 2024 |