English

Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction

Image and Video Processing 2024-07-09 v1 Computer Vision and Pattern Recognition Applied Physics Optics

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 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 GDXRAY dataset.

Keywords

Cite

@article{arxiv.2404.06657,
  title  = {Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction},
  author = {Carlos Osorio Quero and Daniel Leykam and Irving Rondon Ojeda},
  journal= {arXiv preprint arXiv:2404.06657},
  year   = {2024}
}

Comments

16 pages, 8 figures, 4 Tables

R2 v1 2026-06-28T15:49:22.853Z