Cover Image

The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jiatong, Chen, Zheng, Liu, Kai, Wang, Jingkai, Zhou, Zihan, Liu, Xiaoyang, Zhu, Libo, Gong, Jue, Timofte, Radu, Zhang, Yulun, Wang, Congyu, Wang, Zihao, Wu, Ke, Zhu, Xinzhe, Zhang, Fengkai, Yang, Zhongbao, Sun, Long, Dong, Jiangxin, Pan, Jinshan, Tu, Jiachen, Shi, Yaokun, Xu, Guoyi, Jiang, Yaoxin, Liu, Jiajia, Situ, Renyuan, Yang, Yixin, Zhou, Zhaorun, Chen, Junyang, Li, Yuqi, Yang, Chuanguang, Feng, Weilun, Yan, Chuanyue, Tan, Yuedong, Tian, Yingli, Chen, Zhenzhong, Guo, Tongqi, Liu, Ruhan, Shi, Sangzi, Deng, Huazhang, Yang, Jie, Ma, Wenzhuo, Zhang, Yuantong, Yang, Daiqin, Chen, Tianrun, Ji, Deyi, Jiang, Yuxiao, Zhu, Qi, Zhu, Lanyun, Pan, Yuwen, Tian, Runze, Shi, Mingyu, Feng, Zhanfeng, Bao, Yuanfei, Guo, Jiaming, Pei, Renjing, Di, Xin, Peng, Long, Jiang, Linfeng, Fu, Xueyang, Cao, Yang, Zha, Zhengjun, Lee, Choulhyouc, Weng, Shyang-En, Liao, Yi-Cheng, Tyrakowski, Jorge, Xu, Yu-Syuan, Chiu, Wei-Chen, Huang, Ching-Chun, Im, Yoonjin, Park, Jihye, Chun, Hyungju, Park, Hyunhee, Park, MinKyu, Yu, Xiaoxuan, Zhang, Jianxing, Jiang, Yuxuan, Zeng, Chengxi, Peng, Tianhao, Zhang, Fan, Bull, David, Ruangsang, Watchara, Aramvith, Supavadee, Deng, JiaHao, Zhou, Wei, Huang, Hongyu, Lin, Shaohui, Wang, Zihan, Chen, Yilin, Li, Yunchen, Qiao, Junbo, Li, Wei, Xie, Jiao, He, Gaoqi, Li, Wenxi
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911605576433664
author	Li, Jiatong Chen, Zheng Liu, Kai Wang, Jingkai Zhou, Zihan Liu, Xiaoyang Zhu, Libo Gong, Jue Timofte, Radu Zhang, Yulun Wang, Congyu Wang, Zihao Wu, Ke Zhu, Xinzhe Zhang, Fengkai Yang, Zhongbao Sun, Long Dong, Jiangxin Pan, Jinshan Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Situ, Renyuan Yang, Yixin Zhou, Zhaorun Chen, Junyang Li, Yuqi Yang, Chuanguang Feng, Weilun Yan, Chuanyue Tan, Yuedong Tian, Yingli Chen, Zhenzhong Guo, Tongqi Liu, Ruhan Shi, Sangzi Deng, Huazhang Yang, Jie Ma, Wenzhuo Zhang, Yuantong Yang, Daiqin Chen, Tianrun Ji, Deyi Jiang, Yuxiao Zhu, Qi Zhu, Lanyun Pan, Yuwen Tian, Runze Shi, Mingyu Feng, Zhanfeng Bao, Yuanfei Guo, Jiaming Pei, Renjing Di, Xin Peng, Long Jiang, Linfeng Fu, Xueyang Cao, Yang Zha, Zhengjun Lee, Choulhyouc Weng, Shyang-En Liao, Yi-Cheng Tyrakowski, Jorge Xu, Yu-Syuan Chiu, Wei-Chen Huang, Ching-Chun Im, Yoonjin Park, Jihye Chun, Hyungju Park, Hyunhee Park, MinKyu Yu, Xiaoxuan Zhang, Jianxing Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Bull, David Ruangsang, Watchara Aramvith, Supavadee Deng, JiaHao Zhou, Wei Huang, Hongyu Lin, Shaohui Wang, Zihan Chen, Yilin Li, Yunchen Qiao, Junbo Li, Wei Xie, Jiao He, Gaoqi Li, Wenxi
author_facet	Li, Jiatong Chen, Zheng Liu, Kai Wang, Jingkai Zhou, Zihan Liu, Xiaoyang Zhu, Libo Gong, Jue Timofte, Radu Zhang, Yulun Wang, Congyu Wang, Zihao Wu, Ke Zhu, Xinzhe Zhang, Fengkai Yang, Zhongbao Sun, Long Dong, Jiangxin Pan, Jinshan Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Situ, Renyuan Yang, Yixin Zhou, Zhaorun Chen, Junyang Li, Yuqi Yang, Chuanguang Feng, Weilun Yan, Chuanyue Tan, Yuedong Tian, Yingli Chen, Zhenzhong Guo, Tongqi Liu, Ruhan Shi, Sangzi Deng, Huazhang Yang, Jie Ma, Wenzhuo Zhang, Yuantong Yang, Daiqin Chen, Tianrun Ji, Deyi Jiang, Yuxiao Zhu, Qi Zhu, Lanyun Pan, Yuwen Tian, Runze Shi, Mingyu Feng, Zhanfeng Bao, Yuanfei Guo, Jiaming Pei, Renjing Di, Xin Peng, Long Jiang, Linfeng Fu, Xueyang Cao, Yang Zha, Zhengjun Lee, Choulhyouc Weng, Shyang-En Liao, Yi-Cheng Tyrakowski, Jorge Xu, Yu-Syuan Chiu, Wei-Chen Huang, Ching-Chun Im, Yoonjin Park, Jihye Chun, Hyungju Park, Hyunhee Park, MinKyu Yu, Xiaoxuan Zhang, Jianxing Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Bull, David Ruangsang, Watchara Aramvith, Supavadee Deng, JiaHao Zhou, Wei Huang, Hongyu Lin, Shaohui Wang, Zihan Chen, Yilin Li, Yunchen Qiao, Junbo Li, Wei Xie, Jiao He, Gaoqi Li, Wenxi
contents	This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through unknown degradations with a x4 scaling factor while ensuring the models remain executable on mobile devices. The objective is to develop effective and efficient network designs or solutions that achieve state-of-the-art real-world image super-resolution performance. The track of the challenge evaluates performance using a weighted combination of image quality assessment (IQA) score and speedup ratios. The competition attracted 108 registrants, with 16 teams achieving a valid score in the final ranking. This collaborative effort advances the performance of mobile real-world image super-resolution while offering an in-depth overview of the latest trends in the field.
format	Preprint
id	arxiv_https___arxiv_org_abs_2604_17306
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview Li, Jiatong Chen, Zheng Liu, Kai Wang, Jingkai Zhou, Zihan Liu, Xiaoyang Zhu, Libo Gong, Jue Timofte, Radu Zhang, Yulun Wang, Congyu Wang, Zihao Wu, Ke Zhu, Xinzhe Zhang, Fengkai Yang, Zhongbao Sun, Long Dong, Jiangxin Pan, Jinshan Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Situ, Renyuan Yang, Yixin Zhou, Zhaorun Chen, Junyang Li, Yuqi Yang, Chuanguang Feng, Weilun Yan, Chuanyue Tan, Yuedong Tian, Yingli Chen, Zhenzhong Guo, Tongqi Liu, Ruhan Shi, Sangzi Deng, Huazhang Yang, Jie Ma, Wenzhuo Zhang, Yuantong Yang, Daiqin Chen, Tianrun Ji, Deyi Jiang, Yuxiao Zhu, Qi Zhu, Lanyun Pan, Yuwen Tian, Runze Shi, Mingyu Feng, Zhanfeng Bao, Yuanfei Guo, Jiaming Pei, Renjing Di, Xin Peng, Long Jiang, Linfeng Fu, Xueyang Cao, Yang Zha, Zhengjun Lee, Choulhyouc Weng, Shyang-En Liao, Yi-Cheng Tyrakowski, Jorge Xu, Yu-Syuan Chiu, Wei-Chen Huang, Ching-Chun Im, Yoonjin Park, Jihye Chun, Hyungju Park, Hyunhee Park, MinKyu Yu, Xiaoxuan Zhang, Jianxing Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Bull, David Ruangsang, Watchara Aramvith, Supavadee Deng, JiaHao Zhou, Wei Huang, Hongyu Lin, Shaohui Wang, Zihan Chen, Yilin Li, Yunchen Qiao, Junbo Li, Wei Xie, Jiao He, Gaoqi Li, Wenxi Computer Vision and Pattern Recognition This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through unknown degradations with a x4 scaling factor while ensuring the models remain executable on mobile devices. The objective is to develop effective and efficient network designs or solutions that achieve state-of-the-art real-world image super-resolution performance. The track of the challenge evaluates performance using a weighted combination of image quality assessment (IQA) score and speedup ratios. The competition attracted 108 registrants, with 16 teams achieving a valid score in the final ranking. This collaborative effort advances the performance of mobile real-world image super-resolution while offering an in-depth overview of the latest trends in the field.
title	The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2604.17306