NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results

This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Yulun, Zhang, Kai, Chen, Zheng, Li, Yawei, Timofte, Radu, Zhang, Junpei, Zhang, Kexin, Peng, Rui, Ma, Yanbiao, Jia, Licheng, Huang, Huaibo, Zhou, Xiaoqiang, Ai, Yuang, He, Ran, Qiu, Yajun, Zhu, Qiang, Li, Pengfei, Li, Qianhui, Zhu, Shuyuan, Zhang, Dafeng, Li, Jia, Wang, Fan, Li, Chunmiao, Kim, TaeHyung, Kil, Jungkeong, Kim, Eon, Yu, Yeonseung, Lee, Beomyeol, Lee, Subin, Lim, Seokjae, Chae, Somi, Choi, Heungjun, Huang, ZhiKai, Chen, YiChung, Chiang, YuanChun, Yang, HaoHsiang, Chen, WeiTing, Chang, HuaEn, Chen, I-Hsiang, Hsieh, ChiaHsuan, Kuo, SyYen, Choi, Ui-Jin, Conde, Marcos V., Khowaja, Sunder Ali, Yoon, Jiseok, Lee, Ik Hyun, Gendy, Garas, Sabor, Nabil, Hou, Jingchao, He, Guanghui, Zhang, Zhao, Li, Baiang, Zheng, Huan, Zhao, Suiyi, Gao, Yangcheng, Wei, Yanyan, Ren, Jiahuan, Wei, Jiayu, Li, Yanfeng, Sun, Jia, Cheng, Zhanyi, Li, Zhiyuan, Yao, Xu, Wang, Xinyi, Li, Danxu, Cui, Xuan, Cao, Jun, Li, Cheng, Zheng, Jianbin, Sarvaiya, Anjali, Prajapati, Kalpesh, Patra, Ratnadeep, Barik, Pragnesh, Rathod, Chaitanya, Upla, Kishor, Raja, Kiran, Ramachandra, Raghavendra, Busch, Christoph
Format: Conference Proceeding
Language:English
Subjects:
Data models
Focusing
Image restoration
Neural networks
Particle measurements
Superresolution
Transformers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired LR-HR images. The aim of the challenge is to obtain a network design/solution capable to produce high-quality results with the best performance (e.g., PSNR). We want to explore how high performance we can achieve regardless of computational cost (e.g., model size and FLOPs) and data. The track of the challenge was to measure the restored HR images with the ground truth HR images on DIV2K testing dataset. The ranking of the teams is determined directly by the PSNR value. The challenge has attracted 192 registered participants, where 15 teams made valid submissions. They achieve state-of-the-art performance in single image super-resolution.
ISSN:2160-7516
DOI:10.1109/CVPRW59228.2023.00185