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

Code

• github.com/yangyucheng000/MSpaper/tree/main/u2net
  mindspore★ 0

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.

Tasks

Reproductions