Buchumschlag

NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chen, Zheng, Wu, Zongwei, Zamfir, Eduard, Zhang, Kai, Zhang, Yulun, Timofte, Radu, Yang, Xiaokang, Yu, Hongyuan, Wan, Cheng, Hong, Yuxin, Huang, Zhijuan, Zou, Yajun, Huang, Yuan, Lin, Jiamin, Han, Bingnan, Guan, Xianyu, Yu, Yongsheng, Zhang, Daoan, Yin, Xuanwu, Zuo, Kunlong, Hao, Jinhua, Zhao, Kai, Yuan, Kun, Sun, Ming, Zhou, Chao, An, Hongyu, Zhang, Xinfeng, Song, Zhiyuan, Dong, Ziyue, Zhao, Qing, Xu, Xiaogang, Wei, Pengxu, Dou, Zhi-chao, Wang, Gui-ling, Hsu, Chih-Chung, Lee, Chia-Ming, Chou, Yi-Shiuan, Korkmaz, Cansu, Tekalp, A. Murat, Wei, Yubin, Yan, Xiaole, Li, Binren, Chen, Haonan, Zhang, Siqi, Chen, Sihan, Joshi, Amogh, Akalwadi, Nikhil, Malagi, Sampada, Yashaswini, Palani, Desai, Chaitra, Tabib, Ramesh Ashok, Patil, Ujwala, Mudenagudi, Uma, Sarvaiya, Anjali, Choksy, Pooja, Joshi, Jagrit, Kawa, Shubh, Upla, Kishor, Patwardhan, Sushrut, Ramachandra, Raghavendra, Hossain, Sadat, Park, Geongi, Uddin, S. M. Nadim, Xu, Hao, Guo, Yanhui, Urumbekov, Aman, Yan, Xingzhuo, Hao, Wei, Fu, Minghan, Orais, Isaac, Smith, Samuel, Liu, Ying, Jia, Wangwang, Xu, Qisheng, Xu, Kele, Yuan, Weijun, Li, Zhan, Kuang, Wenqin, Guan, Ruijin, Deng, Ruting, Zhang, Zhao, Wang, Bo, Zhao, Suiyi, Luo, Yan, Wei, Yanyan, Khan, Asif Hussain, Micheloni, Christian, Martinel, Niki
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866916206518206464
author	Chen, Zheng Wu, Zongwei Zamfir, Eduard Zhang, Kai Zhang, Yulun Timofte, Radu Yang, Xiaokang Yu, Hongyuan Wan, Cheng Hong, Yuxin Huang, Zhijuan Zou, Yajun Huang, Yuan Lin, Jiamin Han, Bingnan Guan, Xianyu Yu, Yongsheng Zhang, Daoan Yin, Xuanwu Zuo, Kunlong Hao, Jinhua Zhao, Kai Yuan, Kun Sun, Ming Zhou, Chao An, Hongyu Zhang, Xinfeng Song, Zhiyuan Dong, Ziyue Zhao, Qing Xu, Xiaogang Wei, Pengxu Dou, Zhi-chao Wang, Gui-ling Hsu, Chih-Chung Lee, Chia-Ming Chou, Yi-Shiuan Korkmaz, Cansu Tekalp, A. Murat Wei, Yubin Yan, Xiaole Li, Binren Chen, Haonan Zhang, Siqi Chen, Sihan Joshi, Amogh Akalwadi, Nikhil Malagi, Sampada Yashaswini, Palani Desai, Chaitra Tabib, Ramesh Ashok Patil, Ujwala Mudenagudi, Uma Sarvaiya, Anjali Choksy, Pooja Joshi, Jagrit Kawa, Shubh Upla, Kishor Patwardhan, Sushrut Ramachandra, Raghavendra Hossain, Sadat Park, Geongi Uddin, S. M. Nadim Xu, Hao Guo, Yanhui Urumbekov, Aman Yan, Xingzhuo Hao, Wei Fu, Minghan Orais, Isaac Smith, Samuel Liu, Ying Jia, Wangwang Xu, Qisheng Xu, Kele Yuan, Weijun Li, Zhan Kuang, Wenqin Guan, Ruijin Deng, Ruting Zhang, Zhao Wang, Bo Zhao, Suiyi Luo, Yan Wei, Yanyan Khan, Asif Hussain Micheloni, Christian Martinel, Niki
author_facet	Chen, Zheng Wu, Zongwei Zamfir, Eduard Zhang, Kai Zhang, Yulun Timofte, Radu Yang, Xiaokang Yu, Hongyuan Wan, Cheng Hong, Yuxin Huang, Zhijuan Zou, Yajun Huang, Yuan Lin, Jiamin Han, Bingnan Guan, Xianyu Yu, Yongsheng Zhang, Daoan Yin, Xuanwu Zuo, Kunlong Hao, Jinhua Zhao, Kai Yuan, Kun Sun, Ming Zhou, Chao An, Hongyu Zhang, Xinfeng Song, Zhiyuan Dong, Ziyue Zhao, Qing Xu, Xiaogang Wei, Pengxu Dou, Zhi-chao Wang, Gui-ling Hsu, Chih-Chung Lee, Chia-Ming Chou, Yi-Shiuan Korkmaz, Cansu Tekalp, A. Murat Wei, Yubin Yan, Xiaole Li, Binren Chen, Haonan Zhang, Siqi Chen, Sihan Joshi, Amogh Akalwadi, Nikhil Malagi, Sampada Yashaswini, Palani Desai, Chaitra Tabib, Ramesh Ashok Patil, Ujwala Mudenagudi, Uma Sarvaiya, Anjali Choksy, Pooja Joshi, Jagrit Kawa, Shubh Upla, Kishor Patwardhan, Sushrut Ramachandra, Raghavendra Hossain, Sadat Park, Geongi Uddin, S. M. Nadim Xu, Hao Guo, Yanhui Urumbekov, Aman Yan, Xingzhuo Hao, Wei Fu, Minghan Orais, Isaac Smith, Samuel Liu, Ying Jia, Wangwang Xu, Qisheng Xu, Kele Yuan, Weijun Li, Zhan Kuang, Wenqin Guan, Ruijin Deng, Ruting Zhang, Zhao Wang, Bo Zhao, Suiyi Luo, Yan Wei, Yanyan Khan, Asif Hussain Micheloni, Christian Martinel, Niki
contents	This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.
format	Preprint
id	arxiv_https___arxiv_org_abs_2404_09790
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results Chen, Zheng Wu, Zongwei Zamfir, Eduard Zhang, Kai Zhang, Yulun Timofte, Radu Yang, Xiaokang Yu, Hongyuan Wan, Cheng Hong, Yuxin Huang, Zhijuan Zou, Yajun Huang, Yuan Lin, Jiamin Han, Bingnan Guan, Xianyu Yu, Yongsheng Zhang, Daoan Yin, Xuanwu Zuo, Kunlong Hao, Jinhua Zhao, Kai Yuan, Kun Sun, Ming Zhou, Chao An, Hongyu Zhang, Xinfeng Song, Zhiyuan Dong, Ziyue Zhao, Qing Xu, Xiaogang Wei, Pengxu Dou, Zhi-chao Wang, Gui-ling Hsu, Chih-Chung Lee, Chia-Ming Chou, Yi-Shiuan Korkmaz, Cansu Tekalp, A. Murat Wei, Yubin Yan, Xiaole Li, Binren Chen, Haonan Zhang, Siqi Chen, Sihan Joshi, Amogh Akalwadi, Nikhil Malagi, Sampada Yashaswini, Palani Desai, Chaitra Tabib, Ramesh Ashok Patil, Ujwala Mudenagudi, Uma Sarvaiya, Anjali Choksy, Pooja Joshi, Jagrit Kawa, Shubh Upla, Kishor Patwardhan, Sushrut Ramachandra, Raghavendra Hossain, Sadat Park, Geongi Uddin, S. M. Nadim Xu, Hao Guo, Yanhui Urumbekov, Aman Yan, Xingzhuo Hao, Wei Fu, Minghan Orais, Isaac Smith, Samuel Liu, Ying Jia, Wangwang Xu, Qisheng Xu, Kele Yuan, Weijun Li, Zhan Kuang, Wenqin Guan, Ruijin Deng, Ruting Zhang, Zhao Wang, Bo Zhao, Suiyi Luo, Yan Wei, Yanyan Khan, Asif Hussain Micheloni, Christian Martinel, Niki Computer Vision and Pattern Recognition This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.
title	NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2404.09790