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

Zheng Chen, Zongwei Wu, Eduard Zamfir, Kai Zhang, Yulun Zhang +83 more
4/15/2024
cs.CV

No official code found. Best implementation: zhengchen1999/NTIRE2024_ImageSR_x4 (27 stars, MIT, last commit 2025-06-12).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

zhengchen1999/NTIRE2024_ImageSR_x4Community100%
MIT

Solution of the NTIRE 2024 Challenge on Image Super-Resolution (x4)

278Shell, PythonMar 20, 20241 years agoMIT

Similar Papers

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

91% match1 repo1052024

NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results

89% match2024

AIM 2024 Challenge on UHD Blind Photo Quality Assessment

86% match2024

AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results

83% match2024

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark

83% match2025

AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution

83% match2025

Cite this paper

@article{chen2024ntire,
  title  = {NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results},
  author = {Zheng Chen and Zongwei Wu and Eduard Zamfir and Kai Zhang and Yulun Zhang and Radu Timofte and Xiaokang Yang and Hongyuan Yu and Cheng Wan and Yuxin Hong and Zhijuan Huang and Yajun Zou and Yuan Huang and Jiamin Lin and Bingnan Han and Xianyu Guan and Yongsheng Yu and Daoan Zhang and Xuanwu Yin and Kunlong Zuo and Jinhua Hao and Kai Zhao and Kun Yuan and Ming Sun and Chao Zhou and Hongyu An and Xinfeng Zhang and Zhiyuan Song and Ziyue Dong and Qing Zhao and Xiaogang Xu and Pengxu Wei and Zhi-chao Dou and Gui-ling Wang and Chih-Chung Hsu and Chia-Ming Lee and Yi-Shiuan Chou and Cansu Korkmaz and A. Murat Tekalp and Yubin Wei and Xiaole Yan and Binren Li and Haonan Chen and Siqi Zhang and Sihan Chen and Amogh Joshi and Nikhil Akalwadi and Sampada Malagi and Palani Yashaswini and Chaitra Desai and Ramesh Ashok Tabib and Ujwala Patil and Uma Mudenagudi and Anjali Sarvaiya and Pooja Choksy and Jagrit Joshi and Shubh Kawa and Kishor Upla and Sushrut Patwardhan and Raghavendra Ramachandra and Sadat Hossain and Geongi Park and S. M. Nadim Uddin and Hao Xu and Yanhui Guo and Aman Urumbekov and Xingzhuo Yan and Wei Hao and Minghan Fu and Isaac Orais and Samuel Smith and Ying Liu and Wangwang Jia and Qisheng Xu and Kele Xu and Weijun Yuan and Zhan Li and Wenqin Kuang and Ruijin Guan and Ruting Deng and Zhao Zhang and Bo Wang and Suiyi Zhao and Yan Luo and Yanyan Wei and Asif Hussain Khan and Christian Micheloni and Niki Martinel},
  year   = {2024},
  eprint = {2404.09790},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.09790v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.09790.svg)](https://codeofpaper.com/paper/2404.09790)

Discussion