Single-image reflection removal using conditional GANs

Miran Heo, Yoonsik Choe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Removing undesired reflections from a single-image is inherently ill-posed problem since defining its exact physical model is almost impossible. Most previous works tackle this problem through the use of multiple images or hand-crafted features. These methods are still quite limited in terms of the generality and photo-realistic result. In this paper, we propose a conditional Generative Adversarial Networks based deep neural network structure to render realistic image and formulate our problem in a simple objective function. Specifically, we use gradient information to elaborate this formulation to preserve both low and high frequency details. Our proposed network does not rely on any physical prior information and performs effectively with a single-image. Experimental results demonstrate that proposed algorithm conducts favorably against existing algorithms from human perceptual aspect.

Original languageEnglish
Title of host publicationICEIC 2019 - International Conference on Electronics, Information, and Communication
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9788995004449
DOIs
Publication statusPublished - 2019 May 3
Event18th International Conference on Electronics, Information, and Communication, ICEIC 2019 - Auckland, New Zealand
Duration: 2019 Jan 222019 Jan 25

Publication series

NameICEIC 2019 - International Conference on Electronics, Information, and Communication

Conference

Conference18th International Conference on Electronics, Information, and Communication, ICEIC 2019
CountryNew Zealand
CityAuckland
Period19/1/2219/1/25

Fingerprint

Deep neural networks

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Heo, M., & Choe, Y. (2019). Single-image reflection removal using conditional GANs. In ICEIC 2019 - International Conference on Electronics, Information, and Communication [8706433] (ICEIC 2019 - International Conference on Electronics, Information, and Communication). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ELINFOCOM.2019.8706433
Heo, Miran ; Choe, Yoonsik. / Single-image reflection removal using conditional GANs. ICEIC 2019 - International Conference on Electronics, Information, and Communication. Institute of Electrical and Electronics Engineers Inc., 2019. (ICEIC 2019 - International Conference on Electronics, Information, and Communication).
@inproceedings{0a4e973e5c494fbc9cb74b47dea9577a,
title = "Single-image reflection removal using conditional GANs",
abstract = "Removing undesired reflections from a single-image is inherently ill-posed problem since defining its exact physical model is almost impossible. Most previous works tackle this problem through the use of multiple images or hand-crafted features. These methods are still quite limited in terms of the generality and photo-realistic result. In this paper, we propose a conditional Generative Adversarial Networks based deep neural network structure to render realistic image and formulate our problem in a simple objective function. Specifically, we use gradient information to elaborate this formulation to preserve both low and high frequency details. Our proposed network does not rely on any physical prior information and performs effectively with a single-image. Experimental results demonstrate that proposed algorithm conducts favorably against existing algorithms from human perceptual aspect.",
author = "Miran Heo and Yoonsik Choe",
year = "2019",
month = "5",
day = "3",
doi = "10.23919/ELINFOCOM.2019.8706433",
language = "English",
series = "ICEIC 2019 - International Conference on Electronics, Information, and Communication",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICEIC 2019 - International Conference on Electronics, Information, and Communication",
address = "United States",

}

Heo, M & Choe, Y 2019, Single-image reflection removal using conditional GANs. in ICEIC 2019 - International Conference on Electronics, Information, and Communication., 8706433, ICEIC 2019 - International Conference on Electronics, Information, and Communication, Institute of Electrical and Electronics Engineers Inc., 18th International Conference on Electronics, Information, and Communication, ICEIC 2019, Auckland, New Zealand, 19/1/22. https://doi.org/10.23919/ELINFOCOM.2019.8706433

Single-image reflection removal using conditional GANs. / Heo, Miran; Choe, Yoonsik.

ICEIC 2019 - International Conference on Electronics, Information, and Communication. Institute of Electrical and Electronics Engineers Inc., 2019. 8706433 (ICEIC 2019 - International Conference on Electronics, Information, and Communication).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Single-image reflection removal using conditional GANs

AU - Heo, Miran

AU - Choe, Yoonsik

PY - 2019/5/3

Y1 - 2019/5/3

N2 - Removing undesired reflections from a single-image is inherently ill-posed problem since defining its exact physical model is almost impossible. Most previous works tackle this problem through the use of multiple images or hand-crafted features. These methods are still quite limited in terms of the generality and photo-realistic result. In this paper, we propose a conditional Generative Adversarial Networks based deep neural network structure to render realistic image and formulate our problem in a simple objective function. Specifically, we use gradient information to elaborate this formulation to preserve both low and high frequency details. Our proposed network does not rely on any physical prior information and performs effectively with a single-image. Experimental results demonstrate that proposed algorithm conducts favorably against existing algorithms from human perceptual aspect.

AB - Removing undesired reflections from a single-image is inherently ill-posed problem since defining its exact physical model is almost impossible. Most previous works tackle this problem through the use of multiple images or hand-crafted features. These methods are still quite limited in terms of the generality and photo-realistic result. In this paper, we propose a conditional Generative Adversarial Networks based deep neural network structure to render realistic image and formulate our problem in a simple objective function. Specifically, we use gradient information to elaborate this formulation to preserve both low and high frequency details. Our proposed network does not rely on any physical prior information and performs effectively with a single-image. Experimental results demonstrate that proposed algorithm conducts favorably against existing algorithms from human perceptual aspect.

UR - http://www.scopus.com/inward/record.url?scp=85065861555&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065861555&partnerID=8YFLogxK

U2 - 10.23919/ELINFOCOM.2019.8706433

DO - 10.23919/ELINFOCOM.2019.8706433

M3 - Conference contribution

AN - SCOPUS:85065861555

T3 - ICEIC 2019 - International Conference on Electronics, Information, and Communication

BT - ICEIC 2019 - International Conference on Electronics, Information, and Communication

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Heo M, Choe Y. Single-image reflection removal using conditional GANs. In ICEIC 2019 - International Conference on Electronics, Information, and Communication. Institute of Electrical and Electronics Engineers Inc. 2019. 8706433. (ICEIC 2019 - International Conference on Electronics, Information, and Communication). https://doi.org/10.23919/ELINFOCOM.2019.8706433