Learning Rank-1 Diffractive Optics for Single-shot High Dynamic Range Imaging(oral)

Qilin Sun, Ethan Tseng, Qiang Fu, Wolfgang Heidrich, Felix Heide
IEEE CVPR, June, 2020


main
Figure 1: Framework for end-to-end designing and stagelized reconstruction.

Abstract

High-dynamic range (HDR) imaging is an essential imaging modality for a wide range of applications in uncontrolled environments, including autonomous driving, robotics, and mobile phone cameras. However, existing HDR techniques in commodity devices struggle with dynamic scenes due to multi-shot acquisition and post- processing time, e.g. mobile phone burst photography, making such approaches unsuitable for real-time applications. In this work, we propose a method for snapshot HDR imaging by learning an optical HDR encoding in a single image which maps saturated highlights into neighboring unsaturated areas using a diffractive optical element (DOE). We propose a novel rank-1 parameterization of the proposed DOE which avoids vast trainable parameters and keeps high frequencies' encoding compared with conventional end-to-end design methods. We further propose a reconstruction network tailored to this rank-1 parametrization for recovery of clipped information from the encoded measurements. The proposed end-to-end framework is validated through simulation and real-world experiments and improves the PSNR by more than 7 dB over state-of-the-art end-to-end designs.

Resources

Paper: [Sun2020LearningRank1HDR.pdf (~18MB)] 
SuppDoc: [Sun2020LearningRank1HDR_supp.pdf (~39MB)] 
Code&Data will be available on github: [Coming Soon] 
All images are © IEEE Xplore, reproduced here by permission of IEEE Xplore for your personal use. Not for redistribution.

Citation

  @article{Sun2020LearningRank1HDR,
  title={Learning Rank-1 Diffractive Optics for Single-shot High Dynamic Range Imaging},
  author={Sun, Qilin and Tseng, Ethan and Fu, Qiang and Heidrich, Wolfgang and Heide, Felix},
  journal={IEEE CVPR},
  year={2020},
  publisher={IEEE}
  }