NTIRE 2022 Burst Super-Resolution Challenge

Goutam Bhat; Martin Danelljan; Radu Timofte; Yizhen Cao; Yuntian Cao; Meiya Chen; Xihao Chen; Shen Cheng; Akshay Dudhane; Haoqiang Fan; Ruipeng Gang; Jian Gao; Yan Gu; Jie Huang; Liufeng Huang; Youngsu Jo; Sukju Kang; Salman Khan; Fahad Shahbaz Khan; Yuki Kondo; Chenghua Li; Fangya Li; Jinjing Li; Youwei Li; Zechao Li; Chenming Liu; Shuaicheng Liu; Zikun Liu; Zhuoming Liu; Ziwei Luo; Zhengxiong Luo; Nancy Mehta; Subrahmanyam Murala; Yoonchan Nam; Chihiro Nakatani; Pavel Ostyakov; Jinshan Pan; Ge Song; Jian Sun; Long Sun; Jinhui Tang; Norimichi Ukita; Zhihong Wen; Qi Wu; Xiaohe Wu; Zeyu Xiao; Zhiwei Xiong; Rongjian Xu; Ruikang Xu; Youliang Yan; Jialin Yang; Wentao Yang; Zhongbao Yang; Fuma Yasue; Mingde Yao; Lei Yu; Cong Zhang; Syed Waqas Zamir; Jianxing Zhang; Shuohao Zhang; Zhilu Zhang; Qian Zheng; Gaofeng Zhou; Magauiya Zhussip; Xueyi Zou; Wangmeng Zuo

doi:10.1109/CVPRW56347.2022.00117

NTIRE 2022 Burst Super-Resolution Challenge

Goutam Bhat
, Martin Danelljan
, Radu Timofte
, Yizhen Cao
, Yuntian Cao
, Meiya Chen
, Xihao Chen
, Shen Cheng
, Akshay Dudhane
, Haoqiang Fan
, Ruipeng Gang
, Jian Gao
, Yan Gu
, Jie Huang
, Liufeng Huang
, Youngsu Jo
, Sukju Kang
, Salman Khan
, Fahad Shahbaz Khan
, Yuki Kondo

Chenghua Li, Fangya Li, Jinjing Li, Youwei Li, Zechao Li, Chenming Liu, Shuaicheng Liu, Zikun Liu, Zhuoming Liu, Ziwei Luo, Zhengxiong Luo, Nancy Mehta, Subrahmanyam Murala, Yoonchan Nam, Chihiro Nakatani, Pavel Ostyakov, Jinshan Pan, Ge Song, Jian Sun, Long Sun, Jinhui Tang, Norimichi Ukita, Zhihong Wen, Qi Wu, Xiaohe Wu, Zeyu Xiao, Zhiwei Xiong, Rongjian Xu, Ruikang Xu, Youliang Yan, Jialin Yang, Wentao Yang, Zhongbao Yang, Fuma Yasue, Mingde Yao, Lei Yu, Cong Zhang, Syed Waqas Zamir, Jianxing Zhang, Shuohao Zhang, Zhilu Zhang, Qian Zheng, Gaofeng Zhou, Magauiya Zhussip, Xueyi Zou, Wangmeng Zuo

Faculty of Computing

ETH Zurich
University of Würzburg
Communication University of China
Xiaomi
Uestc
Megvii Technology Limited
South China University of Technology
Harbin Institute of Technology
Chinese Academy of Sciences
Nanjing University of Science and Technology
Huawei Technologies Co., Ltd.
University of Science and Technology of China
Whu
Sogang University
Toyota Technological Institute
Linköping University
Australian National University
Inception Institute of Artificial Intelligence
Indian Institute of Technology Ropar
Casia
SRC-B
Uhdtv Research and Application Laboratory
University of Electronic Science and Technology of China
Ustc

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

28 Scopus citations

Abstract

Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4× higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.

Original language	English
Title of host publication	Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Publisher	IEEE Computer Society
Pages	1040-1060
Number of pages	21
ISBN (Electronic)	9781665487399
DOIs	https://doi.org/10.1109/CVPRW56347.2022.00117
State	Published - 2022
Event	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 - New Orleans, United States Duration: 19 Jun 2022 → 24 Jun 2022

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2022-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Country/Territory	United States
City	New Orleans
Period	19/06/22 → 24/06/22

Access to Document

10.1109/CVPRW56347.2022.00117

Cite this

Bhat, G., Danelljan, M., Timofte, R., Cao, Y., Cao, Y., Chen, M., Chen, X., Cheng, S., Dudhane, A., Fan, H., Gang, R., Gao, J., Gu, Y., Huang, J., Huang, L., Jo, Y., Kang, S., Khan, S., Shahbaz Khan, F., ... Zuo, W. (2022). NTIRE 2022 Burst Super-Resolution Challenge. In Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 (pp. 1040-1060). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2022-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW56347.2022.00117

@inproceedings{46d95c4d3b114528b3e6ab548e4d8819,

title = "NTIRE 2022 Burst Super-Resolution Challenge",

abstract = "Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4× higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.",

author = "Goutam Bhat and Martin Danelljan and Radu Timofte and Yizhen Cao and Yuntian Cao and Meiya Chen and Xihao Chen and Shen Cheng and Akshay Dudhane and Haoqiang Fan and Ruipeng Gang and Jian Gao and Yan Gu and Jie Huang and Liufeng Huang and Youngsu Jo and Sukju Kang and Salman Khan and \{Shahbaz Khan\}, Fahad and Yuki Kondo and Chenghua Li and Fangya Li and Jinjing Li and Youwei Li and Zechao Li and Chenming Liu and Shuaicheng Liu and Zikun Liu and Zhuoming Liu and Ziwei Luo and Zhengxiong Luo and Nancy Mehta and Subrahmanyam Murala and Yoonchan Nam and Chihiro Nakatani and Pavel Ostyakov and Jinshan Pan and Ge Song and Jian Sun and Long Sun and Jinhui Tang and Norimichi Ukita and Zhihong Wen and Qi Wu and Xiaohe Wu and Zeyu Xiao and Zhiwei Xiong and Rongjian Xu and Ruikang Xu and Youliang Yan and Jialin Yang and Wentao Yang and Zhongbao Yang and Fuma Yasue and Mingde Yao and Lei Yu and Cong Zhang and \{Waqas Zamir\}, Syed and Jianxing Zhang and Shuohao Zhang and Zhilu Zhang and Qian Zheng and Gaofeng Zhou and Magauiya Zhussip and Xueyi Zou and Wangmeng Zuo",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 ; Conference date: 19-06-2022 Through 24-06-2022",

year = "2022",

doi = "10.1109/CVPRW56347.2022.00117",

language = "英语",

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

publisher = "IEEE Computer Society",

pages = "1040--1060",

booktitle = "Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022",

address = "美国",

}

Bhat, G, Danelljan, M, Timofte, R, Cao, Y, Cao, Y, Chen, M, Chen, X, Cheng, S, Dudhane, A, Fan, H, Gang, R, Gao, J, Gu, Y, Huang, J, Huang, L, Jo, Y, Kang, S, Khan, S, Shahbaz Khan, F, Kondo, Y, Li, C, Li, F, Li, J, Li, Y, Li, Z, Liu, C, Liu, S, Liu, Z, Liu, Z, Luo, Z, Luo, Z, Mehta, N, Murala, S, Nam, Y, Nakatani, C, Ostyakov, P, Pan, J, Song, G, Sun, J, Sun, L, Tang, J, Ukita, N, Wen, Z, Wu, Q, Wu, X, Xiao, Z, Xiong, Z, Xu, R, Xu, R, Yan, Y, Yang, J, Yang, W, Yang, Z, Yasue, F, Yao, M, Yu, L, Zhang, C, Waqas Zamir, S, Zhang, J, Zhang, S, Zhang, Z, Zheng, Q, Zhou, G, Zhussip, M, Zou, X & Zuo, W 2022, NTIRE 2022 Burst Super-Resolution Challenge. in Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2022-June, IEEE Computer Society, pp. 1040-1060, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022, New Orleans, United States, 19/06/22. https://doi.org/10.1109/CVPRW56347.2022.00117

NTIRE 2022 Burst Super-Resolution Challenge. / Bhat, Goutam; Danelljan, Martin; Timofte, Radu et al.
Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022. IEEE Computer Society, 2022. p. 1040-1060 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2022-June).

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

TY - GEN

T1 - NTIRE 2022 Burst Super-Resolution Challenge

AU - Bhat, Goutam

AU - Danelljan, Martin

AU - Timofte, Radu

AU - Cao, Yizhen

AU - Cao, Yuntian

AU - Chen, Meiya

AU - Chen, Xihao

AU - Cheng, Shen

AU - Dudhane, Akshay

AU - Fan, Haoqiang

AU - Gang, Ruipeng

AU - Gao, Jian

AU - Gu, Yan

AU - Huang, Jie

AU - Huang, Liufeng

AU - Jo, Youngsu

AU - Kang, Sukju

AU - Khan, Salman

AU - Shahbaz Khan, Fahad

AU - Kondo, Yuki

AU - Li, Chenghua

AU - Li, Fangya

AU - Li, Jinjing

AU - Li, Youwei

AU - Li, Zechao

AU - Liu, Chenming

AU - Liu, Shuaicheng

AU - Liu, Zikun

AU - Liu, Zhuoming

AU - Luo, Ziwei

AU - Luo, Zhengxiong

AU - Mehta, Nancy

AU - Murala, Subrahmanyam

AU - Nam, Yoonchan

AU - Nakatani, Chihiro

AU - Ostyakov, Pavel

AU - Pan, Jinshan

AU - Song, Ge

AU - Sun, Jian

AU - Sun, Long

AU - Tang, Jinhui

AU - Ukita, Norimichi

AU - Wen, Zhihong

AU - Wu, Qi

AU - Wu, Xiaohe

AU - Xiao, Zeyu

AU - Xiong, Zhiwei

AU - Xu, Rongjian

AU - Xu, Ruikang

AU - Yan, Youliang

AU - Yang, Jialin

AU - Yang, Wentao

AU - Yang, Zhongbao

AU - Yasue, Fuma

AU - Yao, Mingde

AU - Yu, Lei

AU - Zhang, Cong

AU - Waqas Zamir, Syed

AU - Zhang, Jianxing

AU - Zhang, Shuohao

AU - Zhang, Zhilu

AU - Zheng, Qian

AU - Zhou, Gaofeng

AU - Zhussip, Magauiya

AU - Zou, Xueyi

AU - Zuo, Wangmeng

PY - 2022

Y1 - 2022

N2 - Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4× higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.

AB - Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4× higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.

UR - https://www.scopus.com/pages/publications/85129515098

U2 - 10.1109/CVPRW56347.2022.00117

DO - 10.1109/CVPRW56347.2022.00117

M3 - 会议稿件

AN - SCOPUS:85129515098

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

SP - 1040

EP - 1060

BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022

PB - IEEE Computer Society

T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022

Y2 - 19 June 2022 through 24 June 2022

ER -

Bhat G, Danelljan M, Timofte R, Cao Y, Cao Y, Chen M et al. NTIRE 2022 Burst Super-Resolution Challenge. In Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022. IEEE Computer Society. 2022. p. 1040-1060. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW56347.2022.00117

NTIRE 2022 Burst Super-Resolution Challenge

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this