pith. machine review for the scientific record. sign in

arxiv: 2604.21312 · v1 · submitted 2026-04-23 · 💻 cs.CV · cs.AI

Recognition: unknown

The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

Kai Liu , Haoyang Yue , Zeli Lin , Zheng Chen , Jingkai Wang , Jue Gong , Jiatong Li , Xianglong Yan
show 60 more authors
Libo Zhu Jianze Li Ziqing Zhang Zihan Zhou Xiaoyang Liu Radu Timofte Yulun Zhang Junye Chen Zhenming Yan Yucong Hong Ruize Han Song Wang Li Pang Heng Zhao Xinqiao Wu Deyu Meng Xiangyong Cao Weijun Yuan Zhan Li Zhanglu Chen Boyang Yao Yihang Chen Yifan Deng Zengyuan Zuo Junjun Jiang Saiprasad Meesiyawar Sulocha Yatageri Nikhil Akalwadi Ramesh Ashok Tabib Uma Mudenagudi Jiachen Tu Yaokun Shi Guoyi Xu Yaoxin Jiang Cici Liu Tongyao Mu Qiong Cao Yifan Wang Kosuke Shigematsu Hiroto Shirono Asuka Shin Wei Zhou Linfeng Li Lingdong Kong Ce Wang Xingwei Zhong Wanjie Sun Dafeng Zhang Hongxin Lan Qisheng Xu Mingyue He Hui Geng Tianjiao Wan Kele Xu Changjian Wang Antoine Carreaud Nicola Santacroce Shanci Li Jan Skaloud Adrien Gressin
Authors on Pith no claims yet

Pith reviewed 2026-05-09 22:09 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords remote sensinginfrared image super-resolutionNTIRE challengebicubic downsamplingx4 scalingimage benchmarkhigh-resolution recovery
0
0 comments X

The pith

The NTIRE 2026 challenge benchmarks x4 super-resolution of remote sensing infrared images from bicubic-downsampled inputs.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper reports on the first dedicated NTIRE challenge for recovering high-resolution infrared images from low-resolution inputs in remote sensing. The setup uses a single track where low-resolution images are created by applying bicubic downsampling at a factor of four, with the goal of finding models that perform well on this task. One hundred fifteen teams registered and thirteen produced valid submissions, allowing the organizers to compare results and summarize representative methods. The effort positions the challenge as a standard reference point for developing solutions suited to infrared data characteristics and practical remote sensing needs.

Core claim

The challenge is structured as a single-track competition that supplies synthetic low-resolution infrared images generated exclusively through bicubic downsampling at x4 scale, requires participants to produce corresponding high-resolution outputs, and evaluates submissions on standard image quality metrics to identify top-performing approaches for remote sensing infrared super-resolution.

What carries the argument

The single-track evaluation protocol that applies bicubic x4 downsampling to create low-resolution test inputs and ranks submitted super-resolution models by reconstruction accuracy on held-out infrared remote sensing data.

If this is right

  • Submitted methods establish current performance levels for infrared super-resolution at x4 scale under the synthetic degradation model.
  • The challenge results can guide selection of architectures or training strategies for infrared remote sensing tasks.
  • Future iterations can build on the same dataset and protocol to track progress over time.
  • The benchmark encourages development of models that respect infrared-specific properties such as lower contrast and different noise characteristics.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If real sensor degradations differ substantially from bicubic downsampling, models tuned on this benchmark may require additional adaptation steps before deployment.
  • The availability of a public benchmark could accelerate transfer of techniques from visible-light super-resolution to the infrared domain.
  • Extending the protocol to include multiple degradation types or real paired data would test whether the current top methods generalize beyond the synthetic case.

Load-bearing premise

Bicubic downsampling at x4 scale produces low-resolution images whose degradations match those present in actual remote sensing infrared sensors and environments.

What would settle it

Performance comparison of the top submitted models when tested on real captured low-resolution infrared images from actual remote sensing sensors instead of bicubic-synthesized ones.

Figures

Figures reproduced from arXiv: 2604.21312 by Adrien Gressin, Antoine Carreaud, Asuka Shin, Boyang Yao, Ce Wang, Changjian Wang, Cici Liu, Dafeng Zhang, Deyu Meng, Guoyi Xu, Haoyang Yue, Heng Zhao, Hiroto Shirono, Hongxin Lan, Hui Geng, Jan Skaloud, Jiachen Tu, Jianze Li, Jiatong Li, Jingkai Wang, Jue Gong, Junjun Jiang, Junye Chen, Kai Liu, Kele Xu, Kosuke Shigematsu, Libo Zhu, Linfeng Li, Lingdong Kong, Li Pang, Mingyue He, Nicola Santacroce, Nikhil Akalwadi, Qiong Cao, Qisheng Xu, Radu Timofte, Ramesh Ashok Tabib, Ruize Han, Saiprasad Meesiyawar, Shanci Li, Song Wang, Sulocha Yatageri, Tianjiao Wan, Tongyao Mu, Uma Mudenagudi, Wanjie Sun, Weijun Yuan, Wei Zhou, Xianglong Yan, Xiangyong Cao, Xiaoyang Liu, Xingwei Zhong, Xinqiao Wu, Yaokun Shi, Yaoxin Jiang, Yifan Deng, Yifan Wang, Yihang Chen, Yucong Hong, Yulun Zhang, Zeli Lin, Zengyuan Zuo, Zhanglu Chen, Zhan Li, Zheng Chen, Zhenming Yan, Zihan Zhou, Ziqing Zhang.

Figure 1
Figure 1. Figure 1: Architecture of the proposed Quality-Aware Hybrid Attention Transformer (QAHAT). [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overall architecture of the Progressive Focused Transformer (PFT). [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Inference pipeline of their solution. A low-resolution infrared image is augmented with 8 geometric transforms (4 rota￾tions × 2 flips). Each augmented copy is independently super-resolved by two HAT-L models trained with different strategies. The per-model outputs are inverse-transformed and averaged, then the two model predictions are fused with learned weights (0.45 : 0.55) to produce the final ×4 SR ou… view at source ↗
read the original abstract

This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge, one of the associated challenges of NTIRE 2026. The challenge aims to recover high-resolution (HR) infrared images from low-resolution (LR) inputs generated through bicubic downsampling with a x4 scaling factor. The objective is to develop effective models or solutions that achieve state-of-the-art performance for infrared image SR in remote sensing scenarios. To reflect the characteristics of infrared data and practical application needs, the challenge adopts a single-track setting. A total of 115 participants registered for the competition, with 13 teams submitting valid entries. This report summarizes the challenge design, dataset, evaluation protocol, main results, and the representative methods of each team. The challenge serves as a benchmark to advance research in infrared image super-resolution and promote the development of effective solutions for real-world remote sensing applications.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge. It describes the single-track setup where low-resolution infrared images are generated from high-resolution ones using bicubic downsampling with a factor of 4. The report covers the challenge design, dataset, evaluation protocol, participation details (115 registered, 13 teams submitted valid entries), main results, and overviews of the representative methods from participating teams. The paper claims that the challenge acts as a benchmark to advance research in infrared image super-resolution and promote effective solutions for real-world remote sensing applications.

Significance. If the central claim holds, this work provides a useful standardized benchmark for comparing super-resolution methods on remote sensing infrared imagery, which could stimulate further research in this niche area. The documentation of participation and methods offers insights into current approaches. However, the significance is tempered by the synthetic nature of the data, which may limit direct applicability to real-world scenarios.

major comments (1)
  1. [Abstract] Abstract: The assertion that the challenge promotes 'effective solutions for real-world remote sensing applications' is not supported by evidence in the manuscript, as the low-resolution inputs are generated solely via bicubic downsampling without any comparison to or modeling of real sensor degradations (e.g., atmospheric turbulence or wavelength-specific noise). This assumption is load-bearing for the paper's positioning of the benchmark's practical impact.
minor comments (1)
  1. [Abstract] The abstract lacks specific quantitative results, such as the top PSNR or SSIM scores achieved by winning teams, which would strengthen the summary of main results.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our challenge report. We address the major comment regarding the abstract's claim about real-world applicability below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion that the challenge promotes 'effective solutions for real-world remote sensing applications' is not supported by evidence in the manuscript, as the low-resolution inputs are generated solely via bicubic downsampling without any comparison to or modeling of real sensor degradations (e.g., atmospheric turbulence or wavelength-specific noise). This assumption is load-bearing for the paper's positioning of the benchmark's practical impact.

    Authors: We agree that the challenge uses a synthetic bicubic downsampling degradation model, which is a standard practice in super-resolution benchmarks (including prior NTIRE challenges) to ensure controlled, reproducible evaluation across participants. This setup does not incorporate explicit modeling of real-world infrared sensor effects such as atmospheric turbulence or wavelength-specific noise, and the manuscript does not provide direct comparisons or evidence of transfer to such conditions. The claim in the abstract that the challenge promotes 'effective solutions for real-world remote sensing applications' is therefore not fully supported by the presented evidence. We will revise the abstract (and corresponding statements in the introduction) to more accurately describe the challenge as establishing a standardized benchmark for infrared image super-resolution research, noting that methods developed here may serve as a foundation for future work on real-world degradations. This constitutes a partial revision focused on toning down the positioning while preserving the value of the benchmark results. revision: partial

Circularity Check

0 steps flagged

No circularity: factual benchmark report with no derivations

full rationale

The paper is a competition summary report describing challenge setup, dataset generation via bicubic downsampling, participant submissions, and results. It contains no equations, no claimed derivations, no predictions of new quantities, no fitted parameters presented as outputs, and no self-citation chains used to justify core claims. The statement that the challenge 'serves as a benchmark to advance research... for real-world remote sensing applications' is an explicit purpose statement, not a derived result that reduces to its own inputs. The modeling choice of synthetic LR images is presented as given without any circular reduction or uniqueness proof. This is a standard, self-contained factual overview with no load-bearing circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim relies on the standard assumption in super-resolution challenges that synthetic degradation via bicubic interpolation approximates real-world conditions, which may not hold for actual sensor data.

axioms (1)
  • domain assumption Bicubic downsampling accurately models the image degradation process in remote sensing infrared data.
    The abstract specifies that LR inputs are generated through bicubic downsampling with x4 scaling factor.

pith-pipeline@v0.9.0 · 5749 in / 1365 out tokens · 59117 ms · 2026-05-09T22:09:49.453343+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

67 extracted references · 6 canonical work pages · 1 internal anchor

  1. [1]

    NT-HAZE: A Benchmark Dataset for Re- alistic Night-time Image Dehazing

    Radu Ancuti, Codruta Ancuti, Radu Timofte, and Cos- min Ancuti. NT-HAZE: A Benchmark Dataset for Re- alistic Night-time Image Dehazing . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  2. [2]

    NTIRE 2026 Nighttime Image Dehazing Challenge Report

    Radu Ancuti, Alexandru Brateanu, Florin Vasluianu, Raul Balmez, Ciprian Orhei, Codruta Ancuti, Radu Timofte, Cos- min Ancuti, et al. NTIRE 2026 Nighttime Image Dehazing Challenge Report . InProceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  3. [3]

    NTIRE 2026 Challenge on Single Image Re- flection Removal in the Wild: Datasets, Results, and Meth- ods

    Jie Cai, Kangning Yang, Zhiyuan Li, Florin Vasluianu, Radu Timofte, et al. NTIRE 2026 Challenge on Single Image Re- flection Removal in the Wild: Datasets, Results, and Meth- ods . InProceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR) Workshops,

    2026

  4. [4]

    Activating more pixels in image super- resolution transformer

    Xiangyu Chen, Xintao Wang, Jiantao Zhou, Yu Qiao, and Chao Dong. Activating more pixels in image super- resolution transformer. InCVPR, 2023. 3, 4, 6

    2023

  5. [5]

    Hat: Hybrid attention transformer for image restoration.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2025

    Xiangyu Chen, Xintao Wang, Wenlong Zhang, Xiangtao Kong, Yu Qiao, Jiantao Zhou, and Chao Dong. Hat: Hybrid attention transformer for image restoration.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2025. 6

    2025

  6. [6]

    Dual aggregation transformer for image super-resolution

    Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xi- aokang Yang, and Fisher Yu. Dual aggregation transformer for image super-resolution. InICCV, 2023. 2

    2023

  7. [7]

    The Fourth Challenge on Image Super-Resolution (×4) at NTIRE 2026: Benchmark Results and Method Overview

    Zheng Chen, Kai Liu, Jingkai Wang, Xianglong Yan, Jianze Li, Ziqing Zhang, Jue Gong, Jiatong Li, Lei Sun, Xi- aoyang Liu, Radu Timofte, Yulun Zhang, et al. The Fourth Challenge on Image Super-Resolution (×4) at NTIRE 2026: Benchmark Results and Method Overview . InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR) W...

    2026

  8. [8]

    Low Light Image Enhancement Challenge at NTIRE 2026

    George Ciubotariu, Sharif S M A, Abdur Rehman, Fayaz Ali, Rizwan Ali Naqvi, Marcos Conde, Radu Timofte, et al. Low Light Image Enhancement Challenge at NTIRE 2026 . In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  9. [9]

    High FPS Video Frame Interpolation Challenge at NTIRE 2026

    George Ciubotariu, Zhuyun Zhou, Yeying Jin, Zongwei Wu, Radu Timofte, et al. High FPS Video Frame Interpolation Challenge at NTIRE 2026 . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  10. [10]

    Second-order attention network for single image super-resolution

    Tao Dai, Jianrui Cai, Yongbing Zhang, Shu-Tao Xia, and Lei Zhang. Second-order attention network for single image super-resolution. InCVPR, 2019. 2

    2019

  11. [11]

    Learning a deep convolutional network for image super-resolution

    Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Learning a deep convolutional network for image super-resolution. InECCV, 2014. 1

    2014

  12. [12]

    NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Chal- lenge Report

    Andrei Dumitriu, Aakash Ralhan, Florin Miron, Florin Ta- tui, Radu Tudor Ionescu, Radu Timofte, et al. NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Chal- lenge Report . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, 2026. 2

    2026

  13. [13]

    Conde, Zongwei Wu, Yeying Jin, Radu Timofte, et al

    Omar Elezabi, Marcos V . Conde, Zongwei Wu, Yeying Jin, Radu Timofte, et al. Photography Retouching Trans- fer, NTIRE 2026 Challenge: Report . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  14. [14]

    Generative adversarial nets

    Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. InNeurIPS,

  15. [15]

    Mamba: Linear-Time Sequence Modeling with Selective State Spaces

    Albert Gu and Tri Dao. Mamba: Linear-time sequence modeling with selective state spaces.arXiv preprint arXiv:2312.00752, 2023. 2

    work page Pith review arXiv 2023

  16. [16]

    NTIRE 2026 Challenge on End-to-End Financial Receipt Restoration and Reasoning from Degraded Images: Datasets, Methods and Results

    Bochen Guan, Jinlong Li, Kangning Yang, Chuang Ke, Jie Cai, Florin Vasluianu, Radu Timofte, et al. NTIRE 2026 Challenge on End-to-End Financial Receipt Restoration and Reasoning from Degraded Images: Datasets, Methods and Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, 2026. 2

    2026

  17. [17]

    NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

    Ya-nan Guan, Shaonan Zhang, Hang Guo, Yawen Wang, Xinying Fan, Jie Liang, Hui Zeng, Guanyi Qin, Lishen Qu, Tao Dai, Shu-Tao Xia, Lei Zhang, Radu Timofte, et al. NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3) . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  18. [18]

    MambaIR: A simple baseline for image restoration with state-space model

    Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, and Shu-Tao Xia. MambaIR: A simple baseline for image restoration with state-space model. InECCV, pages 222–241. Springer, 2025. 2

    2025

  19. [19]

    NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

    Aleksandr Gushchin, Khaled Abud, Ekaterina Shumitskaya, Artem Filippov, Georgii Bychkov, Sergey Lavrushkin, Mikhail Erofeev, Anastasia Antsiferova, Changsheng Chen, Shunquan Tan, Radu Timofte, Dmitriy Vatolin, et al. NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild . InProceedings of the IEEE/CVF Conference on Computer Vision and Pa...

    2026

  20. [20]

    Denoising diffu- sion probabilistic models

    Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffu- sion probabilistic models. InNeurIPS, 2020. 2

    2020

  21. [21]

    Robust Deepfake De- tection, NTIRE 2026 Challenge: Report

    Benedikt Hopf, Radu Timofte, et al. Robust Deepfake De- tection, NTIRE 2026 Challenge: Report . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  22. [22]

    NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

    Aleksei Khalin, Egor Ershov, Artem Panshin, Sergey Ko- rchagin, Georgiy Lobarev, Arseniy Terekhin, Sofiia Doro- gova, Amir Shamsutdinov, Yasin Mamedov, Bakhtiyar Khalfin, Bogdan Sheludko, Emil Zilyaev, Nikola Bani ´c, Georgy Perevozchikov, Radu Timofte, et al. NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge . In Proceedings of the IEEE/CVF Con...

    2026

  23. [23]

    Accurate image super-resolution using very deep convolutional net- works

    Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. Accurate image super-resolution using very deep convolutional net- works. InCVPR, 2016. 1

    2016

  24. [24]

    Adam: A Method for Stochastic Optimization

    Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980,

    work page internal anchor Pith review Pith/arXiv arXiv

  25. [25]

    Photo-realistic single image super-resolution using a generative adversarial network

    Christian Ledig, Lucas Theis, Ferenc Husz´ar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. Photo-realistic single image super-resolution using a generative adversarial network. InCVPR, 2017. 2

    2017

  26. [26]

    Li et al

    B. Li et al. RBSFormer: Ray beam search transformer for raw image super-resolution. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024. 6

    2024

  27. [27]

    Distillation-free one-step diffusion for real-world image super-resolution.arXiv preprint arXiv:2410.04224, 2024

    Jianze Li, Jiezhang Cao, Zichen Zou, Xiongfei Su, Xin Yuan, Yulun Zhang, Yong Guo, and Xiaokang Yang. Distillation-free one-step diffusion for real-world image super-resolution.arXiv preprint arXiv:2410.04224, 2024. 2

    work page arXiv 2024

  28. [28]

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

    Jiatong Li, Zheng Chen, Kai Liu, Jingkai Wang, Zihan Zhou, Xiaoyang Liu, Libo Zhu, Radu Timofte, Yulun Zhang, et al. The First Challenge on Mobile Real-World Image Super- Resolution at NTIRE 2026: Benchmark Results and Method Overview . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, 2026. 2

    2026

  29. [29]

    Probing deep into temporal profile makes the in- frared small target detector much better.arXiv preprint arXiv:2506.12766, 2025

    Ruojing Li, Wei An, Yingqian Wang, Xinyi Ying, Yimian Dai, Longguang Wang, Miao Li, Yulan Guo, and Li Liu. Probing deep into temporal profile makes the in- frared small target detector much better.arXiv preprint arXiv:2506.12766, 2025. 5

    work page arXiv 2025

  30. [30]

    Infrared video satellite aerial moving target detection dataset and its evaluation.Journal of Image and Graphics, pages 1–15, 2026

    Ruojing Li, Zhaoxu Li, Nuo Chen, Gaowei Guo, Zechao Dou, Zhengxing Long, Yihang Luo, Yaoyuan Zeng, Wei- dong Sheng, Boyang Li, et al. Infrared video satellite aerial moving target detection dataset and its evaluation.Journal of Image and Graphics, pages 1–15, 2026. 2

    2026

  31. [31]

    NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results

    Xin Li, Jiachao Gong, Xijun Wang, Shiyao Xiong, Bingchen Li, Suhang Yao, Chao Zhou, Zhibo Chen, Radu Timofte, et al. NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results . InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  32. [32]

    NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

    Xin Li, Yeying Jin, Suhang Yao, Beibei Lin, Zhaoxin Fan, Wending Yan, Xin Jin, Zongwei Wu, Bingchen Li, Peishu Shi, Yufei Yang, Yu Li, Zhibo Chen, Bihan Wen, Robby Tan, Radu Timofte, et al. NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results . InProceedings of the IEEE/CVF Con- ference on Computer...

    2026

  33. [33]

    Swinir: Image restoration us- ing swin transformer

    Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, and Radu Timofte. Swinir: Image restoration us- ing swin transformer. InICCVW, 2021. 3

    2021

  34. [34]

    The First Chal- lenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

    Kai Liu, Haoyang Yue, Zeli Lin, Zheng Chen, Jingkai Wang, Jue Gong, Radu Timofte, Yulun Zhang, et al. The First Chal- lenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  35. [35]

    Conde, et al

    Shuhong Liu, Ziteng Cui, Chenyu Bao, Xuangeng Chu, Lin Gu, Bin Ren, Radu Timofte, Marcos V . Conde, et al. 3D Restoration and Reconstruction in Adverse Conditions: Re- alX3D Challenge Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  36. [36]

    NTIRE 2026 X- AIGC Quality Assessment Challenge: Methods and Results

    Xiaohong Liu, Xiongkuo Min, Guangtao Zhai, Qiang Hu, Jiezhang Cao, Yu Zhou, Wei Sun, Farong Wen, Zitong Xu, Yingjie Zhou, Huiyu Duan, Lu Liu, Jiarui Wang, Siqi Luo, Chunyi Li, Li Xu, Zicheng Zhang, Yue Shi, Yubo Wang, Minghong Zhang, Chunchao Guo, Zhichao Hu, Mingtao Chen, Xiele Wu, Xin Ma, Zhaohe Lv, Yuanhao Xue, Jiaqi Wang, Xinxing Sha, Radu Timofte, et...

    2026

  37. [37]

    arXiv preprint arXiv:2401.10166 , year=

    Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, and Yunfan Liu. Vmamba: Visual state space model.arXiv preprint arXiv:2401.10166,

    work page arXiv

  38. [38]

    Swin transformer: Hierarchical vision transformer using shifted windows

    Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, 2021. 2

    2021

  39. [39]

    Progressive focused transformer for single image super- resolution

    Wei Long, Xingyu Zhou, Leheng Zhang, and Shuhang Gu. Progressive focused transformer for single image super- resolution. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2279–2288, 2025. 6

    2025

  40. [40]

    NTIRE 2026 Challenge on Video Saliency Predic- tion: Methods and Results

    Andrey Moskalenko, Alexey Bryncev, Ivan Kosmynin, Kira Shilovskaya, Mikhail Erofeev, Dmitry Vatolin, Radu Timo- fte, et al. NTIRE 2026 Challenge on Video Saliency Predic- tion: Methods and Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  41. [41]

    NTIRE 2026 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results

    Hyunhee Park, Eunpil Park, Sangmin Lee, Radu Timofte, et al. NTIRE 2026 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results . InProceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  42. [42]

    NTIRE 2026 Challenge on Learned Smartphone ISP with Unpaired Data: Methods and Results

    Georgy Perevozchikov, Daniil Vladimirov, Radu Timofte, et al. NTIRE 2026 Challenge on Learned Smartphone ISP with Unpaired Data: Methods and Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR) Workshops, 2026. 2

    2026

  43. [43]

    NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

    Guanyi Qin, Jie Liang, Bingbing Zhang, Lishen Qu, Ya-nan Guan, Hui Zeng, Lei Zhang, Radu Timofte, et al. NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1) . InPro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  44. [44]

    The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

    Xingyu Qiu, Yuqian Fu, Jiawei Geng, Bin Ren, Jiancheng Pan, Zongwei Wu, Hao Tang, Yanwei Fu, Radu Timo- fte, Nicu Sebe, Mohamed Elhoseiny, et al. The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  45. [45]

    NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track2)

    Lishen Qu, Yao Liu, Jie Liang, Hui Zeng, Wen Dai, Ya-nan Guan, Guanyi Qin, Shihao Zhou, Jufeng Yang, Lei Zhang, Radu Timofte, et al. NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track2) . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  46. [46]

    The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

    Bin Ren, Hang Guo, Yan Shu, Jiaqi Ma, Ziteng Cui, Shuhong Liu, Guofeng Mei, Lei Sun, Zongwei Wu, Fahad Shahbaz Khan, Salman Khan, Radu Timofte, Yawei Li, et al. The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, 2026. 2

    2026

  47. [47]

    Image super- resolution via iterative refinement.TPAMI, 2022

    Chitwan Saharia, Jonathan Ho, William Chan, Tim Sali- mans, David J Fleet, and Mohammad Norouzi. Image super- resolution via iterative refinement.TPAMI, 2022. 2

    2022

  48. [48]

    Conde, Jeffrey Chen, Zhuyun Zhou, Zongwei Wu, Radu Timofte, et al

    Tim Seizinger, Florin-Alexandru Vasluianu, Marcos V . Conde, Jeffrey Chen, Zhuyun Zhou, Zongwei Wu, Radu Timofte, et al. The First Controllable Bokeh Rendering Challenge at NTIRE 2026 . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  49. [49]

    Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network

    Wenzhe Shi, Jose Caballero, Ferenc Husz ´ar, Johannes Totz, Andrew P Aitken, Rob Bishop, Daniel Rueckert, and Zehan Wang. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In CVPR, 2016. 6

    2016

  50. [50]

    The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results

    Lei Sun, Hang Guo, Bin Ren, Shaolin Su, Xian Wang, Danda Pani Paudel, Luc Van Gool, Radu Timofte, Yawei Li, et al. The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results . InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  51. [51]

    The Second Challenge on Event-Based Image Deblurring at NTIRE 2026: Methods and Results

    Lei Sun, Weilun Li, Xian Wang, Zhendong Li, Letian Shi, Dannong Xu, Deheng Zhang, Mengshun Hu, Shuang Guo, Shaolin Su, Radu Timofte, Danda Pani Paudel, Luc Van Gool, et al. The Second Challenge on Event-Based Image Deblurring at NTIRE 2026: Methods and Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Wor...

    2026

  52. [52]

    NTIRE 2026 The First Challenge on Blind Computational Aberration Correction: Methods and Results

    Lei Sun, Xiaolong Qian, Qi Jiang, Xian Wang, Yao Gao, Kailun Yang, Kaiwei Wang, Radu Timofte, Danda Pani Paudel, Luc Van Gool, et al. NTIRE 2026 The First Challenge on Blind Computational Aberration Correction: Methods and Results . InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  53. [53]

    Seven ways to improve example-based single image super resolu- tion

    Radu Timofte, Rasmus Rothe, and Luc Van Gool. Seven ways to improve example-based single image super resolu- tion. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 1865–1873, 2016. 6, 8

    2016

  54. [54]

    Learning- Based Ambient Lighting Normalization: NTIRE 2026 Chal- lenge Results and Findings

    Florin-Alexandru Vasluianu, Tim Seizinger, Jeffrey Chen, Zhuyun Zhou, Zongwei Wu, Radu Timofte, et al. Learning- Based Ambient Lighting Normalization: NTIRE 2026 Chal- lenge Results and Findings . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  55. [55]

    Advances in Single- Image Shadow Removal: Results from the NTIRE 2026 Challenge

    Florin-Alexandru Vasluianu, Tim Seizinger, Zhuyun Zhou, Zongwei Wu, Radu Timofte, et al. Advances in Single- Image Shadow Removal: Results from the NTIRE 2026 Challenge . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, 2026. 2

    2026

  56. [56]

    Attention is all you need.NeurIPS, 2017

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszko- reit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need.NeurIPS, 2017. 2

    2017

  57. [57]

    The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results

    Jingkai Wang, Jue Gong, Zheng Chen, Kai Liu, Jiatong Li, Yulun Zhang, Radu Timofte, et al. The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results . InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, 2026. 2

    2026

  58. [58]

    NTIRE 2026 Challenge on 3D Content Super-Resolution: Methods and Results

    Longguang Wang, Yulan Guo, Yingqian Wang, Juncheng Li, Sida Peng, Ye Zhang, Radu Timofte, Minglin Chen, Yi Wang, Qibin Hu, Wenjie Lei, et al. NTIRE 2026 Challenge on 3D Content Super-Resolution: Methods and Results . In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  59. [59]

    NTIRE 2026 Challenge on Light Field Image Super-Resolution: Methods and Results

    Yingqian Wang, Zhengyu Liang, Fengyuan Zhang, Wending Zhao, Longguang Wang, Juncheng Li, Jungang Yang, Radu Timofte, Yulan Guo, et al. NTIRE 2026 Challenge on Light Field Image Super-Resolution: Methods and Results . In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  60. [60]

    Seesr: Towards semantics-aware real-world image super-resolution

    Rongyuan Wu, Tao Yang, Lingchen Sun, Zhengqiang Zhang, Shuai Li, and Lei Zhang. Seesr: Towards semantics-aware real-world image super-resolution. InCVPR, 2024. 2

    2024

  61. [61]

    Diffir: Efficient diffusion model for image restoration.arXiv preprint arXiv:2303.09472, 2023

    Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xing- long Wu, Yapeng Tian, Wenming Yang, and Luc Van Gool. Diffir: Efficient diffusion model for image restoration.arXiv preprint arXiv:2303.09472, 2023. 2

    work page arXiv 2023

  62. [62]

    Efficient Low Light Image Enhancement: NTIRE 2026 Challenge Report

    Jiebin Yan, Chenyu Tu, Qinghua Lin, Zongwei WU, Weixia Zhang, Zhihua Wang, Peibei Cao, Yuming Fang, Xiaoning Liu, Zhuyun Zhou, Radu Timofte, et al. Efficient Low Light Image Enhancement: NTIRE 2026 Challenge Report . In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  63. [63]

    NTIRE 2026 Challenge on High- Resolution Depth of non-Lambertian Surfaces

    Pierluigi Zama Ramirez, Fabio Tosi, Luigi Di Stefano, Radu Timofte, Alex Costanzino, Matteo Poggi, Samuele Salti, Ste- fano Mattoccia, et al. NTIRE 2026 Challenge on High- Resolution Depth of non-Lambertian Surfaces . InProceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  64. [64]

    Image super-resolution using very deep residual channel attention networks

    Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image super-resolution using very deep residual channel attention networks. InECCV, 2018. 1

    2018

  65. [65]

    Residual dense network for image super-resolution

    Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. Residual dense network for image super-resolution. InCVPR, 2018. 2

    2018

  66. [66]

    NTIRE 2026 Challenge Report on Anomaly Detection of Face Enhancement for UGC Images

    Yan Zhong, Qiufang Ma, Zhen Wang, Tingting Jiang, Radu Timofte, et al. NTIRE 2026 Challenge Report on Anomaly Detection of Face Enhancement for UGC Images . InPro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026

  67. [67]

    NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Meth- ods and Results

    Wenbin Zou, Tianyi Liu, Kejun Wu, Huiping Zhuang, Zong- wei Wu, Zhuyun Zhou, Radu Timofte, et al. NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Meth- ods and Results . InProceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 2

    2026