English

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

Computer Vision and Pattern Recognition 2026-04-21 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2604.17306,
  title  = {The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview},
  author = {Jiatong Li and Zheng Chen and Kai Liu and Jingkai Wang and Zihan Zhou and Xiaoyang Liu and Libo Zhu and Jue Gong and Radu Timofte and Yulun Zhang and Congyu Wang and Zihao Wang and Ke Wu and Xinzhe Zhu and Fengkai Zhang and Zhongbao Yang and Long Sun and Jiangxin Dong and Jinshan Pan and Jiachen Tu and Yaokun Shi and Guoyi Xu and Yaoxin Jiang and Jiajia Liu and Renyuan Situ and Yixin Yang and Zhaorun Zhou and Junyang Chen and Yuqi Li and Chuanguang Yang and Weilun Feng and Chuanyue Yan and Yuedong Tan and Yingli Tian and Zhenzhong Chen and Tongqi Guo and Ruhan Liu and Sangzi Shi and Huazhang Deng and Jie Yang and Wenzhuo Ma and Yuantong Zhang and Daiqin Yang and Tianrun Chen and Deyi Ji and Yuxiao Jiang and Qi Zhu and Lanyun Zhu and Yuwen Pan and Runze Tian and Mingyu Shi and Zhanfeng Feng and Yuanfei Bao and Jiaming Guo and Renjing Pei and Xin Di and Long Peng and Linfeng Jiang and Xueyang Fu and Yang Cao and Zhengjun Zha and Choulhyouc Lee and Shyang-En Weng and Yi-Cheng Liao and Jorge Tyrakowski and Yu-Syuan Xu and Wei-Chen Chiu and Ching-Chun Huang and Yoonjin Im and Jihye Park and Hyungju Chun and Hyunhee Park and MinKyu Park and Xiaoxuan Yu and Jianxing Zhang and Yuxuan Jiang and Chengxi Zeng and Tianhao Peng and Fan Zhang and David Bull and Watchara Ruangsang and Supavadee Aramvith and JiaHao Deng and Wei Zhou and Hongyu Huang and Shaohui Lin and Zihan Wang and Yilin Chen and Yunchen Li and Junbo Qiao and Wei Li and Jiao Xie and Gaoqi He and Wenxi Li},
  journal= {arXiv preprint arXiv:2604.17306},
  year   = {2026}
}

Comments

NTIRE 2026 webpage: https://cvlai.net/ntire/2026/. Code: https://github.com/jiatongli2024/NTIRE2026_Mobile_RealWorld_ImageSR