Single-shot compressed ultrafast photography based on U-net network

Tools

Zhang, Anke and Wu, Jiamin and Suo, Jinli and Fang, Lu and Qiao, Hui and Li, David Day-Uei and Zhang, Shian and Fan, Jiantao and Qi, Dalong and Dai, Qionghai and Pei, Chengquan (2020) Single-shot compressed ultrafast photography based on U-net network. Optics Express, 28 (26). pp. 39299-39310. 398083. ISSN 1094-4087 (https://doi.org/10.1364/OE.398083)

[thumbnail of Zhang-etal-OE-2020-Single-shot-compressed-ultrafast-photography-based-on-U-net]
Preview
 Text. Filename: Zhang_etal_OE_2020_Single_shot_compressed_ultrafast_photography_based_on_U_net.pdf
Final Published Version
License: Other
Download (10MB)| Preview

Abstract

The compressive ultrafast photography (CUP) has achieved real-time femtosecond imaging based on the compressive-sensing methods. However, the reconstruction performance usually suffers from artifacts brought by strong noise, aberration, and distortion, which prevents its applications. We propose a deep compressive ultrafast photography (DeepCUP) method. Various numerical simulations have been demonstrated on both the MNIST and UCF-101 datasets and compared with other state-of-the-art algorithms. The result shows that our DeepCUP has a superior performance in both PSNR and SSIM compared to previous compressed-sensing methods. We also illustrate the outstanding performance of the proposed method under system errors and noise in comparison to other methods.

ORCID iDs

Zhang, Anke, Wu, Jiamin, Suo, Jinli, Fang, Lu, Qiao, Hui, Li, David Day-Uei ORCID logoORCID: https://orcid.org/0000-0002-6401-4263, Zhang, Shian, Fan, Jiantao, Qi, Dalong, Dai, Qionghai and Pei, Chengquan;
CORE (COnnecting REpositories)