End-to-End Computational Lensless Imaging with Perceptual Loss

Ya Ti Chang Lee; Chung Hao Tien

doi:10.36463/idw.2022.1153

End-to-End Computational Lensless Imaging with Perceptual Loss

Ya Ti Chang Lee, Chung Hao Tien

光電工程學系

研究成果 › 同行評審

摘要

Recently, computational lensless imaging had been making progress with the evolution of artificial neural networks. Nonetheless, generative models for image reconstruction inherit challenge due to its ill-posed nature. We proposed a deep neural network based lensless imaging system by optimizing perceptual loss exclusively to end-to-end reconstruct images conforming human preference.

原文	English
頁（從 - 到）	1153-1156
頁數	4
期刊	Proceedings of the International Display Workshops
卷	29
DOIs	https://doi.org/10.36463/idw.2022.1153
出版狀態	Published - 2022
事件	29th International Display Workshops, IDW 2022 - Fukuoka, 日本持續時間: 14 12月 2022 → 16 12月 2022

存取文件

10.36463/idw.2022.1153

其它文件與鏈接

Link to publication in Scopus

引用此

@article{304d6dbdfdac42eca84015426e290fa8,

title = "End-to-End Computational Lensless Imaging with Perceptual Loss",

abstract = "Recently, computational lensless imaging had been making progress with the evolution of artificial neural networks. Nonetheless, generative models for image reconstruction inherit challenge due to its ill-posed nature. We proposed a deep neural network based lensless imaging system by optimizing perceptual loss exclusively to end-to-end reconstruct images conforming human preference.",

keywords = "Lensless imaging, artificial neural network, coded aperture, perceptual loss",

author = "Lee, \{Ya Ti Chang\} and Tien, \{Chung Hao\}",

note = "Publisher Copyright: {\textcopyright} 2022 ITE and SID.; 29th International Display Workshops, IDW 2022 ; Conference date: 14-12-2022 Through 16-12-2022",

year = "2022",

doi = "10.36463/idw.2022.1153",

language = "English",

volume = "29",

pages = "1153--1156",

journal = "Proceedings of the International Display Workshops",

issn = "1883-2490",

publisher = "International Display Workshops",

}

TY - JOUR

T1 - End-to-End Computational Lensless Imaging with Perceptual Loss

AU - Lee, Ya Ti Chang

AU - Tien, Chung Hao

PY - 2022

Y1 - 2022

N2 - Recently, computational lensless imaging had been making progress with the evolution of artificial neural networks. Nonetheless, generative models for image reconstruction inherit challenge due to its ill-posed nature. We proposed a deep neural network based lensless imaging system by optimizing perceptual loss exclusively to end-to-end reconstruct images conforming human preference.

AB - Recently, computational lensless imaging had been making progress with the evolution of artificial neural networks. Nonetheless, generative models for image reconstruction inherit challenge due to its ill-posed nature. We proposed a deep neural network based lensless imaging system by optimizing perceptual loss exclusively to end-to-end reconstruct images conforming human preference.

KW - Lensless imaging

KW - artificial neural network

KW - coded aperture

KW - perceptual loss

UR - https://www.scopus.com/pages/publications/85175256743

U2 - 10.36463/idw.2022.1153

DO - 10.36463/idw.2022.1153

M3 - Conference article

AN - SCOPUS:85175256743

SN - 1883-2490

VL - 29

SP - 1153

EP - 1156

JO - Proceedings of the International Display Workshops

JF - Proceedings of the International Display Workshops

T2 - 29th International Display Workshops, IDW 2022

Y2 - 14 December 2022 through 16 December 2022

ER -

End-to-End Computational Lensless Imaging with Perceptual Loss

摘要

存取文件

其它文件與鏈接

指紋

引用此