Skip to main content

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

Author(s): Sun, Qilin; Tseng, Ethan; Fu, Qiang; Heidrich, Wolfgang; Heide, Felix

To refer to this page use:
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.
Publication Date: 2020
Citation: Sun, Qilin, Ethan Tseng, Qiang Fu, Wolfgang Heidrich, and Felix Heide. "Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020): pp. 1383-1393. doi:10.1109/CVPR42600.2020.00146
DOI: 10.1109/CVPR42600.2020.00146
ISSN: 1063-6919
EISSN: 2575-7075
Pages: 1383 - 1393
Type of Material: Conference Article
Journal/Proceeding Title: IEEE/CVF Conference on Computer Vision and Pattern Recognition
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.