Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging

Qilin Sun, Ethan Tseng, Qiang Fu, Wolfgang Heidrich, Felix Heide; The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1386-1396

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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Sun_2020_CVPR,
author = {Sun, Qilin and Tseng, Ethan and Fu, Qiang and Heidrich, Wolfgang and Heide, Felix},
title = {Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}