Table of Contents: :: Library Catalog

Saved in:

Bibliographic Details
Main Authors:	Ren, Bin, Guo, Hang, Shu, Yan, Ma, Jiaqi, Cui, Ziteng, Liu, Shuhong, Mei, Guofeng, Sun, Lei, Wu, Zongwei, Khan, Fahad Shahbaz, Khan, Salman, Timofte, Radu, Li, Yawei, Yu, Hongyuan, Xu, Pufan, Wu, Chen, Peng, Long, Yi, Jiaojiao, Yi, Siyang, Cui, Yuning, Xia, Jingyuan, Mou, Xing, He, Keji, Wu, Jinlin, Gao, Zongang, Yang, Sen, Zheng, Rui, Li, Fengguo, Lei, Yecheng, Min, Wenkai, Liu, Jie, Cao, Keye, Sharma, Shubham, Prasad, Manish, Li, Haobo, Fazel, Matin, Bentaleb, Abdelhak, Chen, Rui, Shi, Shurui, Dai, Zitao, Liu, Qingliang, Cheng, Yang, Hu, Jing, Zhang, Xuan, Ding, Rui, Zhang, Tingyi, Deng, Hui, Wang, Mengyang, Liu, Fulin, Wei, Jing, Wang, Qian, Liu, Hongying, Li, Mingyang, Dong, Guanglu, Yang, Zheng, Ren, Chao, Fang, Hongbo, Li, Lingxuan, Si, Lin, Gao, Pan, Gabbouj, Moncef, Ruangsang, Watchara, Aramvith, Supavadee
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	https://arxiv.org/abs/2604.03198
Tags:	Add Tag No Tags, Be the first to tag this record!

Table of Contents:

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

Similar Items