Unified Angle Adjustment Network for Image Composition Enhancement

Jinwon Ko; Nyeong Ho Shin; Seonho Lee; Chang Su Kim

doi:10.23919/APSIPAASC55919.2022.9979887

Unified Angle Adjustment Network for Image Composition Enhancement

Jinwon Ko, Nyeong Ho Shin, Seonho Lee, Chang Su Kim

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

Abstract

We propose an angle adjustment algorithm for the composition enhancement of digital photographs. The proposed algorithm jointly learns the scene type, composition, and semantic line information of an image to improve the accuracy of angle adjustment. To this end, we design a unified angle adjustment network (UAAN), which consists of a unified encoder and four task-specific refinement modules and estimators. First, we generate shared features using the unified encoder. Then, we refine those features using the refinement modules to perform the four tasks of angle regression, scene type classification, composition classification, and semantic line detection. Experimental results demonstrate the effectiveness of the proposed UAAN algorithm.

Original language	English
Title of host publication	Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1053-1057
Number of pages	5
ISBN (Electronic)	9786165904773
DOIs	https://doi.org/10.23919/APSIPAASC55919.2022.9979887
Publication status	Published - 2022
Event	2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 - Chiang Mai, Thailand Duration: 2022 Nov 7 → 2022 Nov 10

Publication series

Name	Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

Conference

Conference	2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
Country/Territory	Thailand
City	Chiang Mai
Period	22/11/7 → 22/11/10

Bibliographical note

Funding Information:
This work was supported by the Naver Corporation and the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2022R1A2B5B03002310 and No. NRF-2021R1A4A1031864).

Publisher Copyright:
© 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Access to Document

10.23919/APSIPAASC55919.2022.9979887

Cite this

Ko, J., Shin, N. H., Lee, S., & Kim, C. S. (2022). Unified Angle Adjustment Network for Image Composition Enhancement. In Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 (pp. 1053-1057). (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPAASC55919.2022.9979887

Unified Angle Adjustment Network for Image Composition Enhancement. / Ko, Jinwon; Shin, Nyeong Ho; Lee, Seonho et al.
Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 1053-1057 (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022).

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

Ko, J, Shin, NH, Lee, S & Kim, CS 2022, Unified Angle Adjustment Network for Image Composition Enhancement. in Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 1053-1057, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022, Chiang Mai, Thailand, 22/11/7. https://doi.org/10.23919/APSIPAASC55919.2022.9979887

Ko J, Shin NH, Lee S, Kim CS. Unified Angle Adjustment Network for Image Composition Enhancement. In Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 1053-1057. (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022). doi: 10.23919/APSIPAASC55919.2022.9979887

Ko, Jinwon ; Shin, Nyeong Ho ; Lee, Seonho et al. / Unified Angle Adjustment Network for Image Composition Enhancement. Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 1053-1057 (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022).

@inproceedings{7b3bf26cdbea45c8ad56447f2237e4c9,

title = "Unified Angle Adjustment Network for Image Composition Enhancement",

abstract = "We propose an angle adjustment algorithm for the composition enhancement of digital photographs. The proposed algorithm jointly learns the scene type, composition, and semantic line information of an image to improve the accuracy of angle adjustment. To this end, we design a unified angle adjustment network (UAAN), which consists of a unified encoder and four task-specific refinement modules and estimators. First, we generate shared features using the unified encoder. Then, we refine those features using the refinement modules to perform the four tasks of angle regression, scene type classification, composition classification, and semantic line detection. Experimental results demonstrate the effectiveness of the proposed UAAN algorithm.",

author = "Jinwon Ko and Shin, {Nyeong Ho} and Seonho Lee and Kim, {Chang Su}",

note = "Funding Information: This work was supported by the Naver Corporation and the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2022R1A2B5B03002310 and No. NRF-2021R1A4A1031864). Publisher Copyright: {\textcopyright} 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).; 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 ; Conference date: 07-11-2022 Through 10-11-2022",

year = "2022",

doi = "10.23919/APSIPAASC55919.2022.9979887",

language = "English",

series = "Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1053--1057",

booktitle = "Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022",

}

TY - GEN

T1 - Unified Angle Adjustment Network for Image Composition Enhancement

AU - Ko, Jinwon

AU - Shin, Nyeong Ho

AU - Lee, Seonho

AU - Kim, Chang Su

N1 - Funding Information: This work was supported by the Naver Corporation and the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2022R1A2B5B03002310 and No. NRF-2021R1A4A1031864). Publisher Copyright: © 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).

PY - 2022

Y1 - 2022

N2 - We propose an angle adjustment algorithm for the composition enhancement of digital photographs. The proposed algorithm jointly learns the scene type, composition, and semantic line information of an image to improve the accuracy of angle adjustment. To this end, we design a unified angle adjustment network (UAAN), which consists of a unified encoder and four task-specific refinement modules and estimators. First, we generate shared features using the unified encoder. Then, we refine those features using the refinement modules to perform the four tasks of angle regression, scene type classification, composition classification, and semantic line detection. Experimental results demonstrate the effectiveness of the proposed UAAN algorithm.

AB - We propose an angle adjustment algorithm for the composition enhancement of digital photographs. The proposed algorithm jointly learns the scene type, composition, and semantic line information of an image to improve the accuracy of angle adjustment. To this end, we design a unified angle adjustment network (UAAN), which consists of a unified encoder and four task-specific refinement modules and estimators. First, we generate shared features using the unified encoder. Then, we refine those features using the refinement modules to perform the four tasks of angle regression, scene type classification, composition classification, and semantic line detection. Experimental results demonstrate the effectiveness of the proposed UAAN algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85146260026&partnerID=8YFLogxK

U2 - 10.23919/APSIPAASC55919.2022.9979887

DO - 10.23919/APSIPAASC55919.2022.9979887

M3 - Conference contribution

AN - SCOPUS:85146260026

T3 - Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

SP - 1053

EP - 1057

BT - Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

Y2 - 7 November 2022 through 10 November 2022

ER -

Unified Angle Adjustment Network for Image Composition Enhancement

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this