SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR

Wei Ting Chen; Yi Wen Chen; Kuan Yu Chen; Jian Jiun Ding; Sy Yen Kuo

doi:10.1109/ICIP46576.2022.9898067

SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR

Wei Ting Chen^*, Yi Wen Chen^*, Kuan Yu Chen^*, Jian Jiun Ding^*, Sy Yen Kuo^*

^*Corresponding author for this work

National Taiwan University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Single image reflection removal is a crucial technique which can improve the performance of object detection, semantic segmentation, and various computer vision applications. In this paper, we present a novel reflection removal algorithm using bi-channel priors (i.e., the dark channel prior and the bright channel prior). We observe that the values of dark channel pixels are not near 0, and those of bright channel pixels are not closer to 1 under the reflection scenario. We first demonstrate these phenomena statistically and mathe- matically. Then, we apply these properties as the constraints in optimizing the proposed reflection removal process. Extensive experiments on several well-known benchmarks demonstrate that our approach achieves desirable reflection suppression results compared with other methods.

Original language	English
Title of host publication	2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
Publisher	IEEE Computer Society
Pages	2117-2121
Number of pages	5
ISBN (Electronic)	9781665496209
DOIs	https://doi.org/10.1109/ICIP46576.2022.9898067
State	Published - 2022
Externally published	Yes
Event	29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France Duration: 16 10 2022 → 19 10 2022

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Conference

Conference	29th IEEE International Conference on Image Processing, ICIP 2022
Country/Territory	France
City	Bordeaux
Period	16/10/22 → 19/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Bi-channels prior
Layer separation
Reflection removal

Access to Document

10.1109/ICIP46576.2022.9898067

Cite this

Chen, W. T., Chen, Y. W., Chen, K. Y., Ding, J. J., & Kuo, S. Y. (2022). SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR. In 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings (pp. 2117-2121). (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP46576.2022.9898067

@inproceedings{47768a313c89421ea7291d449f6248eb,

title = "SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR",

abstract = "Single image reflection removal is a crucial technique which can improve the performance of object detection, semantic segmentation, and various computer vision applications. In this paper, we present a novel reflection removal algorithm using bi-channel priors (i.e., the dark channel prior and the bright channel prior). We observe that the values of dark channel pixels are not near 0, and those of bright channel pixels are not closer to 1 under the reflection scenario. We first demonstrate these phenomena statistically and mathe- matically. Then, we apply these properties as the constraints in optimizing the proposed reflection removal process. Extensive experiments on several well-known benchmarks demonstrate that our approach achieves desirable reflection suppression results compared with other methods.",

keywords = "Bi-channels prior, Layer separation, Reflection removal",

author = "Chen, {Wei Ting} and Chen, {Yi Wen} and Chen, {Kuan Yu} and Ding, {Jian Jiun} and Kuo, {Sy Yen}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 29th IEEE International Conference on Image Processing, ICIP 2022 ; Conference date: 16-10-2022 Through 19-10-2022",

year = "2022",

doi = "10.1109/ICIP46576.2022.9898067",

language = "英语",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "2117--2121",

booktitle = "2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings",

address = "美国",

}

Chen, WT, Chen, YW, Chen, KY, Ding, JJ & Kuo, SY 2022, SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR. in 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 2117-2121, 29th IEEE International Conference on Image Processing, ICIP 2022, Bordeaux, France, 16/10/22. https://doi.org/10.1109/ICIP46576.2022.9898067

SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR. / Chen, Wei Ting; Chen, Yi Wen; Chen, Kuan Yu et al.
2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. IEEE Computer Society, 2022. p. 2117-2121 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR

AU - Chen, Wei Ting

AU - Chen, Yi Wen

AU - Chen, Kuan Yu

AU - Ding, Jian Jiun

AU - Kuo, Sy Yen

PY - 2022

Y1 - 2022

N2 - Single image reflection removal is a crucial technique which can improve the performance of object detection, semantic segmentation, and various computer vision applications. In this paper, we present a novel reflection removal algorithm using bi-channel priors (i.e., the dark channel prior and the bright channel prior). We observe that the values of dark channel pixels are not near 0, and those of bright channel pixels are not closer to 1 under the reflection scenario. We first demonstrate these phenomena statistically and mathe- matically. Then, we apply these properties as the constraints in optimizing the proposed reflection removal process. Extensive experiments on several well-known benchmarks demonstrate that our approach achieves desirable reflection suppression results compared with other methods.

AB - Single image reflection removal is a crucial technique which can improve the performance of object detection, semantic segmentation, and various computer vision applications. In this paper, we present a novel reflection removal algorithm using bi-channel priors (i.e., the dark channel prior and the bright channel prior). We observe that the values of dark channel pixels are not near 0, and those of bright channel pixels are not closer to 1 under the reflection scenario. We first demonstrate these phenomena statistically and mathe- matically. Then, we apply these properties as the constraints in optimizing the proposed reflection removal process. Extensive experiments on several well-known benchmarks demonstrate that our approach achieves desirable reflection suppression results compared with other methods.

KW - Bi-channels prior

KW - Layer separation

KW - Reflection removal

UR - http://www.scopus.com/inward/record.url?scp=85146675269&partnerID=8YFLogxK

U2 - 10.1109/ICIP46576.2022.9898067

DO - 10.1109/ICIP46576.2022.9898067

M3 - 会议稿件

AN - SCOPUS:85146675269

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2117

EP - 2121

BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings

PB - IEEE Computer Society

T2 - 29th IEEE International Conference on Image Processing, ICIP 2022

Y2 - 16 October 2022 through 19 October 2022

ER -

SINGLE IMAGE REFLECTION REMOVAL BASED ON BI-CHANNELS PRIOR

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this