Bijective-constrained cycle-consistent deep learning for optics-free imaging and classification

Abstract

Many deep learning approaches to solve computational imaging problems have proven successful through relying solely on the data. However, when applied to the raw output of a bare (optics-free) image sensor, these methods fail to reconstruct target images that are structurally diverse. In this work we propose a self-consistent supervised model that learns not only the inverse, but also the forward model to better constrain the predictions through encouraging the network to model the ideal bijective imaging system. To do this, we employ cycle consistency alongside traditional reconstruction losses, both of which we show are needed for incoherent optics-free image reconstruction. By eliminating all optics, we demonstrate imaging with the thinnest camera possible.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jan 03, 2022
Source ID
10.1364/optica.440575

Entities

People

  • Rajesh Menon
  • Soren Nelson

Organizations

  • National Science Foundation
  • Office of Naval Research
  • University of Utah

Tags

Fields of Study

  • Computer science
  • Physics

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks