Publications
Home
Schools
Computational Sciences
Publications
- Title
- Res-U2Net: untrained deep learning for phase retrieval and image reconstruction
- KIAS Author
- Ojeda, Irving Rondon
- Journal
- JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2024
- Archive
-
- Abstract
- Conventional deep learning -based image reconstruction methods require a large amount of training data, which can be hard to obtain in practice. Untrained deep learning methods overcome this limitation by training a network to invert a physical model of the image formation process. Here we present a novel, to our knowledge, untrained Res-U2Net model for phase retrieval. We use the extracted phase information to determine changes in an object's surface and generate a mesh representation of its 3D structure. We compare the performance of Res-U2Net phase retrieval against UNet and U2Net using images from the GDXRAYdataset. (c) 2024 Optica Publishing Group