MIPI 2023 Challenge on RGBW Remosaic: Methods and Results

Qianhui Sun; Qingyu Yang; Chongyi Li; Shangchen Zhou; Ruicheng Feng; Yuekun Dai; Wenxiu Sun; Qingpeng Zhu; Chen Change Loy; Jinwei Gu; Yuqing Liu; Hongyuan Yu; Weichen Yu; Zhen Dong; Binnan Han; Qi Jia; Xuanwu Yin; Kunlong Zuo; Yaqi Wu; Zhihao Fan; Fanqing Meng; Xun Wu; Jiawei Zhang; Feng Zhang; Mingyan Han; Jinting Luo; Qi Wu; Ting Jiang; Chengzhi Jiang; Wenjie Lin; Xinpeng Li; Lei Yu; Haoqiang Fan; Shuaicheng Liu

doi:10.1109/CVPRW59228.2023.00289

MIPI 2023 Challenge on RGBW Remosaic: Methods and Results

Qianhui Sun, Qingyu Yang, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Yuekun Dai, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Yuqing Liu, Hongyuan Yu, Weichen Yu, Zhen Dong, Binnan Han, Qi Jia, Xuanwu Yin, Kunlong Zuo, Yaqi Wu, Zhihao FanFanqing Meng, Xun Wu, Jiawei Zhang, Feng Zhang, Mingyan Han, Jinting Luo, Qi Wu, Ting Jiang, Chengzhi Jiang, Wenjie Lin, Xinpeng Li, Lei Yu, Haoqiang Fan, Shuaicheng Liu

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

5 Citations (Scopus)

Abstract

Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for an in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). With the success of the 1st MIPI Workshop@ECCV 2022, we introduce the second MIPI challenge, including four tracks focusing on novel image sensors and imaging algorithms. This paper summarizes and reviews the RGBW Joint Remosaic and Denoise track on MIPI 2023. In total, 81 participants were successfully registered, and 4 teams submitted results in the final testing phase. The final results are evaluated using objective metrics, including PSNR, SSIM, LPIPS, and KLD. A detailed description of the top three models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023/.

Original language	English
Title of host publication	Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Publisher	IEEE Computer Society
Pages	2878-2885
Number of pages	8
ISBN (Electronic)	9798350302493
DOIs	https://doi.org/10.1109/CVPRW59228.2023.00289
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Canada Duration: Jun 18 2023 → Jun 22 2023

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2023-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Country/Territory	Canada
City	Vancouver
Period	6/18/23 → 6/22/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

ASJC Scopus Subject Areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW59228.2023.00289

Cite this

Sun, Q., Yang, Q., Li, C., Zhou, S., Feng, R., Dai, Y., Sun, W., Zhu, Q., Loy, C. C., Gu, J., Liu, Y., Yu, H., Yu, W., Dong, Z., Han, B., Jia, Q., Yin, X., Zuo, K., Wu, Y., ... Liu, S. (2023). MIPI 2023 Challenge on RGBW Remosaic: Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 (pp. 2878-2885). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW59228.2023.00289

@inproceedings{3752b03f29b24685ba4386688782965f,

title = "MIPI 2023 Challenge on RGBW Remosaic: Methods and Results",

abstract = "Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for an in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). With the success of the 1st MIPI Workshop@ECCV 2022, we introduce the second MIPI challenge, including four tracks focusing on novel image sensors and imaging algorithms. This paper summarizes and reviews the RGBW Joint Remosaic and Denoise track on MIPI 2023. In total, 81 participants were successfully registered, and 4 teams submitted results in the final testing phase. The final results are evaluated using objective metrics, including PSNR, SSIM, LPIPS, and KLD. A detailed description of the top three models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023/.",

author = "Qianhui Sun and Qingyu Yang and Chongyi Li and Shangchen Zhou and Ruicheng Feng and Yuekun Dai and Wenxiu Sun and Qingpeng Zhu and Loy, \{Chen Change\} and Jinwei Gu and Yuqing Liu and Hongyuan Yu and Weichen Yu and Zhen Dong and Binnan Han and Qi Jia and Xuanwu Yin and Kunlong Zuo and Yaqi Wu and Zhihao Fan and Fanqing Meng and Xun Wu and Jiawei Zhang and Feng Zhang and Mingyan Han and Jinting Luo and Qi Wu and Ting Jiang and Chengzhi Jiang and Wenjie Lin and Xinpeng Li and Lei Yu and Haoqiang Fan and Shuaicheng Liu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 ; Conference date: 18-06-2023 Through 22-06-2023",

year = "2023",

doi = "10.1109/CVPRW59228.2023.00289",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "2878--2885",

booktitle = "Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023",

address = "United States",

}

Sun, Q, Yang, Q, Li, C, Zhou, S, Feng, R, Dai, Y, Sun, W, Zhu, Q, Loy, CC, Gu, J, Liu, Y, Yu, H, Yu, W, Dong, Z, Han, B, Jia, Q, Yin, X, Zuo, K, Wu, Y, Fan, Z, Meng, F, Wu, X, Zhang, J, Zhang, F, Han, M, Luo, J, Wu, Q, Jiang, T, Jiang, C, Lin, W, Li, X, Yu, L, Fan, H & Liu, S 2023, MIPI 2023 Challenge on RGBW Remosaic: Methods and Results. in Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2023-June, IEEE Computer Society, pp. 2878-2885, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, Vancouver, Canada, 6/18/23. https://doi.org/10.1109/CVPRW59228.2023.00289

MIPI 2023 Challenge on RGBW Remosaic: Methods and Results. / Sun, Qianhui; Yang, Qingyu; Li, Chongyi et al.
Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society, 2023. p. 2878-2885 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June).

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

TY - GEN

T1 - MIPI 2023 Challenge on RGBW Remosaic

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

AU - Sun, Qianhui

AU - Yang, Qingyu

AU - Li, Chongyi

AU - Zhou, Shangchen

AU - Feng, Ruicheng

AU - Dai, Yuekun

AU - Sun, Wenxiu

AU - Zhu, Qingpeng

AU - Loy, Chen Change

AU - Gu, Jinwei

AU - Liu, Yuqing

AU - Yu, Hongyuan

AU - Yu, Weichen

AU - Dong, Zhen

AU - Han, Binnan

AU - Jia, Qi

AU - Yin, Xuanwu

AU - Zuo, Kunlong

AU - Wu, Yaqi

AU - Fan, Zhihao

AU - Meng, Fanqing

AU - Wu, Xun

AU - Zhang, Jiawei

AU - Zhang, Feng

AU - Han, Mingyan

AU - Luo, Jinting

AU - Wu, Qi

AU - Jiang, Ting

AU - Jiang, Chengzhi

AU - Lin, Wenjie

AU - Li, Xinpeng

AU - Yu, Lei

AU - Fan, Haoqiang

AU - Liu, Shuaicheng

PY - 2023

Y1 - 2023

N2 - Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for an in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). With the success of the 1st MIPI Workshop@ECCV 2022, we introduce the second MIPI challenge, including four tracks focusing on novel image sensors and imaging algorithms. This paper summarizes and reviews the RGBW Joint Remosaic and Denoise track on MIPI 2023. In total, 81 participants were successfully registered, and 4 teams submitted results in the final testing phase. The final results are evaluated using objective metrics, including PSNR, SSIM, LPIPS, and KLD. A detailed description of the top three models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023/.

AB - Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for an in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). With the success of the 1st MIPI Workshop@ECCV 2022, we introduce the second MIPI challenge, including four tracks focusing on novel image sensors and imaging algorithms. This paper summarizes and reviews the RGBW Joint Remosaic and Denoise track on MIPI 2023. In total, 81 participants were successfully registered, and 4 teams submitted results in the final testing phase. The final results are evaluated using objective metrics, including PSNR, SSIM, LPIPS, and KLD. A detailed description of the top three models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023/.

UR - http://www.scopus.com/inward/record.url?scp=85170822860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85170822860&partnerID=8YFLogxK

U2 - 10.1109/CVPRW59228.2023.00289

DO - 10.1109/CVPRW59228.2023.00289

M3 - Conference contribution

AN - SCOPUS:85170822860

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 2878

EP - 2885

BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

PB - IEEE Computer Society

Y2 - 18 June 2023 through 22 June 2023

ER -

Sun Q, Yang Q, Li C, Zhou S, Feng R, Dai Y et al. MIPI 2023 Challenge on RGBW Remosaic: Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society. 2023. p. 2878-2885. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW59228.2023.00289

MIPI 2023 Challenge on RGBW Remosaic: Methods and Results

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Access to Document

Other files and links

Cite this