Academic Journal
Conditional Variational Autoencoder for Learned Image Reconstruction
| العنوان: | Conditional Variational Autoencoder for Learned Image Reconstruction |
|---|---|
| المؤلفون: | Zhang, C, Barbano, R, Jin, B |
| المصدر: | Computation , 9 (11) , Article 114. (2021) |
| بيانات النشر: | MDPI AG |
| سنة النشر: | 2021 |
| المجموعة: | University College London: UCL Discovery |
| مصطلحات موضوعية: | conditional variational autoencoder, uncertainty quantification, deep learning, image reconstruction |
| الوصف: | Learned image reconstruction techniques using deep neural networks have recently gained popularity and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect information uncertainty. In this work, we develop a novel computational framework that approximates the posterior distribution of the unknown image at each query observation. The proposed framework is very flexible: it handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets. Once the network is trained using the conditional variational autoencoder loss, it provides a computationally efficient sampler for the approximate posterior distribution via feed-forward propagation, and the summarizing statistics of the generated samples are used for both point-estimation and uncertainty quantification. We illustrate the proposed framework with extensive numerical experiments on positron emission tomography (with both moderate and low-count levels) showing that the framework generates high-quality samples when compared with state-of-the-art methods. |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | text |
| اللغة: | English |
| Relation: | https://discovery.ucl.ac.uk/id/eprint/10137615/8/Jin_computation-09-00114.pdf; https://discovery.ucl.ac.uk/id/eprint/10137615/ |
| الاتاحة: | https://discovery.ucl.ac.uk/id/eprint/10137615/8/Jin_computation-09-00114.pdf https://discovery.ucl.ac.uk/id/eprint/10137615/ |
| Rights: | open |
| رقم الانضمام: | edsbas.220A9F1B |
| قاعدة البيانات: | BASE |
| الوصف غير متاح. |