Image Blending Algorithm with Automatic Mask Generation

Haochen Xue; Mingyu Jin; Chong Zhang; Yuxuan Huang; Qian Weng; Xiaobo Jin

doi:10.1007/978-981-99-8132-8_18

Image Blending Algorithm with Automatic Mask Generation

Haochen Xue, Mingyu Jin, Chong Zhang, Yuxuan Huang, Qian Weng, Xiaobo Jin^*

^*Corresponding author for this work

Department of Intelligent Science

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

Abstract

In recent years, image blending has gained popularity for its ability to create visually stunning content. However, the current image blending algorithms mainly have the following problems: manually creating image blending masks requires a lot of manpower and material resources; image blending algorithms cannot effectively solve the problems of brightness distortion and low resolution. To this end, we propose a new image blending method with automatic mask generation: it combines semantic object detection and segmentation with mask generation to achieve deep blended images, while based on our proposed new saturation loss and two-stage iteration of the PAN algorithm to fix brightness distortion and low-resolution issues. Results on publicly available datasets show that our method outperforms other classical image blending algorithms on various performance metrics including PSNR and SSIM.

Original language	English
Title of host publication	Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class
Editors	Biao Luo, Long Cheng, Zheng-Guang Wu, Hongyi Li, Chaojie Li
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	234-248
Number of pages	15
ISBN (Print)	9789819981311
DOIs	https://doi.org/10.1007/978-981-99-8132-8_18
Publication status	Published - 20 Nov 2023
Event	30th International Conference on Neural Information Processing, ICONIP 2023 - Changsha, China Duration: 20 Nov 2023 → 23 Nov 2023

Publication series

Name	Communications in Computer and Information Science
Volume	1962 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	30th International Conference on Neural Information Processing, ICONIP 2023
Country/Territory	China
City	Changsha
Period	20/11/23 → 23/11/23

Keywords

Image Blending
Image Segmentation
Mask Generation
Object Detection

Access to Document

10.1007/978-981-99-8132-8_18

Cite this

Xue, H., Jin, M., Zhang, C., Huang, Y., Weng, Q., & Jin, X. (2023). Image Blending Algorithm with Automatic Mask Generation. In B. Luo, L. Cheng, Z.-G. Wu, H. Li, & C. Li (Eds.), Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class (pp. 234-248). (Communications in Computer and Information Science; Vol. 1962 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-8132-8_18

Xue, Haochen ; Jin, Mingyu ; Zhang, Chong et al. / Image Blending Algorithm with Automatic Mask Generation. Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class. editor / Biao Luo ; Long Cheng ; Zheng-Guang Wu ; Hongyi Li ; Chaojie Li. Springer Science and Business Media Deutschland GmbH, 2023. pp. 234-248 (Communications in Computer and Information Science).

@inproceedings{d7dc6dc7949447558b4b1bdf29d1acb7,

title = "Image Blending Algorithm with Automatic Mask Generation",

abstract = "In recent years, image blending has gained popularity for its ability to create visually stunning content. However, the current image blending algorithms mainly have the following problems: manually creating image blending masks requires a lot of manpower and material resources; image blending algorithms cannot effectively solve the problems of brightness distortion and low resolution. To this end, we propose a new image blending method with automatic mask generation: it combines semantic object detection and segmentation with mask generation to achieve deep blended images, while based on our proposed new saturation loss and two-stage iteration of the PAN algorithm to fix brightness distortion and low-resolution issues. Results on publicly available datasets show that our method outperforms other classical image blending algorithms on various performance metrics including PSNR and SSIM.",

keywords = "Image Blending, Image Segmentation, Mask Generation, Object Detection",

author = "Haochen Xue and Mingyu Jin and Chong Zhang and Yuxuan Huang and Qian Weng and Xiaobo Jin",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 30th International Conference on Neural Information Processing, ICONIP 2023 ; Conference date: 20-11-2023 Through 23-11-2023",

year = "2023",

month = nov,

day = "20",

doi = "10.1007/978-981-99-8132-8_18",

language = "English",

isbn = "9789819981311",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "234--248",

editor = "Biao Luo and Long Cheng and Zheng-Guang Wu and Hongyi Li and Chaojie Li",

booktitle = "Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class",

}

Xue, H, Jin, M, Zhang, C, Huang, Y, Weng, Q & Jin, X 2023, Image Blending Algorithm with Automatic Mask Generation. in B Luo, L Cheng, Z-G Wu, H Li & C Li (eds), Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class. Communications in Computer and Information Science, vol. 1962 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 234-248, 30th International Conference on Neural Information Processing, ICONIP 2023, Changsha, China, 20/11/23. https://doi.org/10.1007/978-981-99-8132-8_18

Image Blending Algorithm with Automatic Mask Generation. / Xue, Haochen; Jin, Mingyu; Zhang, Chong et al.
Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class. ed. / Biao Luo; Long Cheng; Zheng-Guang Wu; Hongyi Li; Chaojie Li. Springer Science and Business Media Deutschland GmbH, 2023. p. 234-248 (Communications in Computer and Information Science; Vol. 1962 CCIS).

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

TY - GEN

T1 - Image Blending Algorithm with Automatic Mask Generation

AU - Xue, Haochen

AU - Jin, Mingyu

AU - Zhang, Chong

AU - Huang, Yuxuan

AU - Weng, Qian

AU - Jin, Xiaobo

PY - 2023/11/20

Y1 - 2023/11/20

N2 - In recent years, image blending has gained popularity for its ability to create visually stunning content. However, the current image blending algorithms mainly have the following problems: manually creating image blending masks requires a lot of manpower and material resources; image blending algorithms cannot effectively solve the problems of brightness distortion and low resolution. To this end, we propose a new image blending method with automatic mask generation: it combines semantic object detection and segmentation with mask generation to achieve deep blended images, while based on our proposed new saturation loss and two-stage iteration of the PAN algorithm to fix brightness distortion and low-resolution issues. Results on publicly available datasets show that our method outperforms other classical image blending algorithms on various performance metrics including PSNR and SSIM.

AB - In recent years, image blending has gained popularity for its ability to create visually stunning content. However, the current image blending algorithms mainly have the following problems: manually creating image blending masks requires a lot of manpower and material resources; image blending algorithms cannot effectively solve the problems of brightness distortion and low resolution. To this end, we propose a new image blending method with automatic mask generation: it combines semantic object detection and segmentation with mask generation to achieve deep blended images, while based on our proposed new saturation loss and two-stage iteration of the PAN algorithm to fix brightness distortion and low-resolution issues. Results on publicly available datasets show that our method outperforms other classical image blending algorithms on various performance metrics including PSNR and SSIM.

KW - Image Blending

KW - Image Segmentation

KW - Mask Generation

KW - Object Detection

UR - http://www.scopus.com/inward/record.url?scp=85178614402&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-8132-8_18

DO - 10.1007/978-981-99-8132-8_18

M3 - Conference Proceeding

AN - SCOPUS:85178614402

SN - 9789819981311

T3 - Communications in Computer and Information Science

SP - 234

EP - 248

BT - Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class

A2 - Luo, Biao

A2 - Cheng, Long

A2 - Wu, Zheng-Guang

A2 - Li, Hongyi

A2 - Li, Chaojie

PB - Springer Science and Business Media Deutschland GmbH

T2 - 30th International Conference on Neural Information Processing, ICONIP 2023

Y2 - 20 November 2023 through 23 November 2023

ER -

Xue H, Jin M, Zhang C, Huang Y, Weng Q, Jin X. Image Blending Algorithm with Automatic Mask Generation. In Luo B, Cheng L, Wu ZG, Li H, Li C, editors, Neural Information Processing - 30th International Conference, ICONIP 2023, CCF C Class. Springer Science and Business Media Deutschland GmbH. 2023. p. 234-248. (Communications in Computer and Information Science). doi: 10.1007/978-981-99-8132-8_18