pith. machine review for the scientific record. sign in

arxiv: 2604.17306 · v1 · submitted 2026-04-19 · 💻 cs.CV

Recognition: unknown

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 , Jue Gong
show 86 more authors
Radu Timofte Yulun Zhang Congyu Wang Zihao Wang Ke Wu Xinzhe Zhu Fengkai Zhang Zhongbao Yang Long Sun Jiangxin Dong Jinshan Pan Jiachen Tu Yaokun Shi Guoyi Xu Yaoxin Jiang Jiajia Liu Renyuan Situ Yixin Yang Zhaorun Zhou Junyang Chen Yuqi Li Chuanguang Yang Weilun Feng Chuanyue Yan Yuedong Tan Yingli Tian Zhenzhong Chen Tongqi Guo Ruhan Liu Sangzi Shi Huazhang Deng Jie Yang Wenzhuo Ma Yuantong Zhang Daiqin Yang Tianrun Chen Deyi Ji Yuxiao Jiang Qi Zhu Lanyun Zhu Yuwen Pan Runze Tian Mingyu Shi Zhanfeng Feng Yuanfei Bao Jiaming Guo Renjing Pei Xin Di Long Peng Linfeng Jiang Xueyang Fu Yang Cao Zhengjun Zha Choulhyouc Lee Shyang-En Weng Yi-Cheng Liao Jorge Tyrakowski Yu-Syuan Xu Wei-Chen Chiu Ching-Chun Huang Yoonjin Im Jihye Park Hyungju Chun Hyunhee Park MinKyu Park Xiaoxuan Yu Jianxing Zhang Yuxuan Jiang Chengxi Zeng Tianhao Peng Fan Zhang David Bull Watchara Ruangsang Supavadee Aramvith JiaHao Deng Wei Zhou Hongyu Huang Shaohui Lin Zihan Wang Yilin Chen Yunchen Li Junbo Qiao Wei Li Jiao Xie Gaoqi He Wenxi Li
Authors on Pith no claims yet

Pith reviewed 2026-05-10 06:05 UTC · model grok-4.3

classification 💻 cs.CV
keywords mobile image super-resolutionreal-world super-resolutionimage quality assessmentefficient neural networksbenchmark resultsmethod overview4x upscalingNTIRE challenge
0
0 comments X

The pith

The NTIRE 2026 challenge on mobile real-world image super-resolution shows that efficient models can recover high-resolution images from unknown low-resolution inputs at 4x scale while running on mobile devices.

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

This paper reviews the outcomes of a challenge that required participants to build super-resolution networks capable of 4x upscaling under unknown real-world degradations, with all models required to execute directly on mobile hardware. It presents the submitted methods from the 16 teams that achieved valid final scores out of 108 registrants and ranks them according to a combined score of image quality assessment and speedup ratio. The review documents current approaches to balancing perceptual quality with computational constraints in this setting. A reader would care because such models enable on-device image enhancement without relying on cloud processing, which matters for privacy, latency, and battery use in consumer cameras and phones.

Core claim

The challenge establishes that state-of-the-art real-world image super-resolution performance is achievable with mobile-executable networks through diverse design choices, evaluated under a weighted metric of image quality assessment scores and speedup ratios, with the collected solutions providing an overview of prevailing trends in efficient network architectures for unknown degradations.

What carries the argument

The weighted IQA-plus-speedup metric that ranks entries by combining perceptual image quality scores with measured inference speedup on target mobile platforms.

If this is right

  • New network designs emerge that maintain high perceptual quality while meeting strict mobile runtime constraints at 4x scaling.
  • The collected methods reveal practical trade-offs between model size, speed, and quality under real degradations.
  • Future work can use the released benchmark and top solutions as a starting point for further efficiency improvements.
  • The ranking system encourages solutions that are simultaneously accurate and fast enough for on-device deployment.

Where Pith is reading between the lines

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

  • These benchmark results may guide integration of super-resolution into mobile camera pipelines for immediate image enhancement.
  • The focus on unknown degradations could lead to training strategies that generalize better across different camera sensors.
  • Extending the challenge format to joint tasks such as denoising plus super-resolution would test broader mobile applicability.

Load-bearing premise

The weighted image quality assessment score combined with speedup ratios reliably measures real-world mobile usability and the challenge's unknown degradations match typical consumer camera conditions.

What would settle it

A field test in which top-ranked models produce visibly inferior results on actual smartphone captures or fail to deliver the claimed speedup when measured on common mobile hardware.

Figures

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

Figure 1
Figure 1. Figure 1: Team Antman dinated to avoid unstable over-enhancement. 2. Knowledge distillation bridges the gap between mas￾sive generative priors and mobile efficiency. To meet the strict parameter and FLOP constraints of mobile deployment, several teams employed distillation strate￾gies to transfer knowledge from heavy teacher mod￾els to lightweight students. For example, the Samsun￾gAICamera team utilized adversarial… view at source ↗
Figure 2
Figure 2. Figure 2: Team SamsungAICamera tural reliability of GANs with the texture generation of diffusion models emerged as a highly effective strategy. 4. Challenge Methods and Teams 4.1. VIPSL Description. VIPSL builds an efficient perceptual SR pipeline around PLKSR-Rep [32], targeting the mobile real￾world setting where both quality and inference efficiency matter. Instead of introducing a heavy architecture, the team k… view at source ↗
Figure 3
Figure 3. Figure 3: Team TODSR between denoising and decoding, as shown in [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Team YuFans LSDIR [36], with degradation generation following PASD settings [77]. Training is run on one RTX4060 GPU, with 512×512 patches and batch size 16; pix-LoRA is trained for 4500 iterations and sem-LoRA for 16000 iterations at initial learning rate 5×10−5 . The team reports a best testing-phase score of 4.2824 and an estimated speedup ratio of 2.8671 over OSEDiff in their benchmark setting. 4.5. Yu… view at source ↗
Figure 5
Figure 5. Figure 5: Team IMAG2006 where LMUSIQ, LCLIPIQA, and LMANIQA are all differen￾tiable and therefore can be used as perceptual supervision signals. For metrics where higher scores indicate better per￾ceptual quality, Team IMAG2006 first normalizes the scores to [0, 1] and then transforms them into minimization objec￾tives by using 1 − s, where s is the normalized score. The total training loss is formulated as: Ltotal … view at source ↗
read the original 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.

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 / 0 minor

Summary. The paper reviews the NTIRE 2026 challenge on mobile real-world image super-resolution. It describes the task of x4 upscaling from low-resolution inputs generated by unknown degradations, with the constraint that models must run on mobile devices. Performance is ranked by a weighted combination of image quality assessment (IQA) scores and speedup ratios. The report notes 108 registrants and 16 teams with valid final scores, summarizes the submitted solutions, and states that the collaborative effort advances mobile real-world SR performance while providing an overview of current trends.

Significance. If the reported rankings and method summaries hold, the paper supplies a useful public benchmark and trend overview for efficient real-world SR under mobile constraints, an area of growing practical importance. It explicitly credits the scale of participation and the compilation of method descriptions from multiple teams.

major comments (1)
  1. [Abstract and Challenge Evaluation] Abstract and Challenge Evaluation section: The claim that the collaborative effort 'advances the performance of mobile real-world image super-resolution' rests on the weighted IQA-plus-speedup ranking under unknown x4 degradations. The manuscript contains no ablation, correlation study against human ratings, or comparison to real captured LR-HR pairs from consumer cameras that would establish whether this composite metric correlates with actual mobile-device usability (latency, power, perceptual quality) or whether the synthetic degradations are representative of typical camera pipelines. This is load-bearing for the advancement interpretation.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the thoughtful feedback on the evaluation metric and the strength of the advancement claim. We address the concern directly below and will revise the manuscript to ensure the interpretation is appropriately qualified.

read point-by-point responses

  1. Referee: Abstract and Challenge Evaluation section: The claim that the collaborative effort 'advances the performance of mobile real-world image super-resolution' rests on the weighted IQA-plus-speedup ranking under unknown x4 degradations. The manuscript contains no ablation, correlation study against human ratings, or comparison to real captured LR-HR pairs from consumer cameras that would establish whether this composite metric correlates with actual mobile-device usability (latency, power, perceptual quality) or whether the synthetic degradations are representative of typical camera pipelines. This is load-bearing for the advancement interpretation.

    Authors: We agree that the manuscript does not contain new ablation studies, human correlation analyses, or direct comparisons against real captured LR-HR pairs from consumer cameras. As a challenge overview paper, the evaluation follows the protocol defined in the NTIRE 2026 challenge call, which combines standard IQA metrics (PSNR, SSIM, LPIPS, NIQE) with measured speedup on mobile hardware to balance quality and efficiency under the constraint of unknown x4 degradations. These degradations are generated using established synthetic pipelines common to real-world SR benchmarks. We acknowledge that validating the composite score against human ratings or real camera pipelines would strengthen claims of practical advancement; however, such studies fall outside the scope of a post-challenge report that summarizes 16 submitted methods. To address the concern, we will revise the abstract and Challenge Evaluation section to replace the phrasing 'advances the performance' with 'provides a public benchmark and overview of current trends in mobile real-world SR', thereby removing the load-bearing interpretation while preserving the factual reporting of participation and rankings. revision: yes

Circularity Check

0 steps flagged

No circularity: factual challenge report with no derivation chain

full rationale

This is a standard NTIRE challenge overview paper that reports external competition results, participant methods, and rankings under a defined track metric. No original mathematical derivation, first-principles model, or prediction is presented that could reduce to its own inputs. The abstract and structure consist of factual summaries of submissions and outcomes; the weighted IQA+speedup evaluation is an external contest rule, not a self-derived claim. No self-citation load-bearing steps, fitted inputs renamed as predictions, or ansatz smuggling occur.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an overview paper of a computer vision challenge with no mathematical models, parameters, or new entities introduced.

pith-pipeline@v0.9.0 · 5838 in / 1103 out tokens · 52781 ms · 2026-05-10T06:05:59.228199+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

89 extracted references · 8 canonical work pages

  1. [1]

    Ntire 2017 challenge on single image super-resolution: Dataset and study

    Eirikur Agustsson and Radu Timofte. Ntire 2017 challenge on single image super-resolution: Dataset and study. In CVPRW, 2017. 2, 5, 6

    2017

  2. [2]

    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

  3. [3]

    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

  4. [4]

    Taesd: Tiny autoencoder for stable diffu- sion, 2023

    Ollin Boer Bohan. Taesd: Tiny autoencoder for stable diffu- sion, 2023. GitHub repository. 4, 5

    2023

  5. [5]

    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

  6. [6]

    Adversarial diffu- sion compression for real-world image super-resolution

    Bin Chen, Gehui Li, Rongyuan Wu, Xindong Zhang, Jie Chen, Jian Zhang, and Lei Zhang. Adversarial diffu- sion compression for real-world image super-resolution. In CVPR, 2025. 6

    2025

  7. [7]

    Faithd- iff: Unleashing diffusion priors for faithful image super- resolution

    Junyang Chen, Jinshan Pan, and Jiangxin Dong. Faithd- iff: Unleashing diffusion priors for faithful image super- resolution. InCVPR, 2025. 6, 8

    2025

  8. [8]

    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

  9. [9]

    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

  10. [10]

    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

  11. [11]

    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

  12. [12]

    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

  13. [13]

    Image quality assessment: Unifying structure and texture similarity.TPAMI, 2020

    Keyan Ding, Kede Ma, Shiqi Wang, and Eero P Simoncelli. Image quality assessment: Unifying structure and texture similarity.TPAMI, 2020. 2, 5, 6, 7

    2020

  14. [14]

    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. 2

    2014

  15. [15]

    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

  16. [16]

    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

  17. [17]

    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,

  18. [18]

    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

  19. [19]

    Div8k: Diverse 8k resolution image dataset

    Shuhang Gu, Andreas Lugmayr, Martin Danelljan, Manuel Fritsche, Julien Lamour, and Radu Timofte. Div8k: Diverse 8k resolution image dataset. In2019 IEEE/CVF Interna- tional Conference on Computer Vision Workshop (ICCVW), pages 3512–3516. IEEE, 2019. 6

    2019

  20. [20]

    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

  21. [21]

    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

  22. [22]

    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

  23. [23]

    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

  24. [24]

    Denoising diffu- sion probabilistic models

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

    2020

  25. [25]

    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

  26. [26]

    Lora: Low-rank adaptation of large language models.ICLR,

    Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. Lora: Low-rank adaptation of large language models.ICLR,

  27. [27]

    A style-based generator architecture for generative adversarial networks

    Tero Karras, Samuli Laine, and Timo Aila. A style-based generator architecture for generative adversarial networks. In CVPR, 2019. 6

    2019

  28. [28]

    Musiq: Multi-scale image quality transformer

    Junjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar, and Feng Yang. Musiq: Multi-scale image quality transformer. InICCV, 2021. 2, 5, 6, 7

    2021

  29. [29]

    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

  30. [30]

    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. 2

    2016

  31. [31]

    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

  32. [32]

    Partial large kernel cnns for efficient super-resolution,

    Dongheon Lee, Seokju Yun, and Youngmin Ro. Partial large kernel cnns for efficient super-resolution.arXiv preprint arXiv:2404.11848, 2024. 5

    work page arXiv 2024

  33. [33]

    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

  34. [34]

    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

  35. [35]

    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

  36. [36]

    Lsdir: A large scale dataset for image restoration

    Yawei Li, Kai Zhang, Jingyun Liang, Jiezhang Cao, Ce Liu, Rui Gong, Yulun Zhang, Hao Tang, Yun Liu, Denis Deman- dolx, et al. Lsdir: A large scale dataset for image restoration. InCVPRW, 2023. 2, 6, 7

    2023

  37. [37]

    Enhanced deep residual networks for single image super-resolution

    Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. Enhanced deep residual networks for single image super-resolution. InCVPRW, 2017. 4

    2017

  38. [38]

    Diff- bir: Toward blind image restoration with generative diffusion prior

    Xinqi Lin, Jingwen He, Ziyan Chen, Zhaoyang Lyu, Bo Dai, Fanghua Yu, Wanli Ouyang, Yu Qiao, and Chao Dong. Diff- bir: Toward blind image restoration with generative diffusion prior. InECCV, 2024. 7

    2024

  39. [39]

    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

  40. [40]

    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

  41. [41]

    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

  42. [42]

    VMamba: Visual state space model,

    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

  43. [43]

    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

  44. [44]

    Decoupled weight decay regularization

    Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. InICLR, 2019. 6

    2019

  45. [45]

    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

  46. [46]

    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

  47. [47]

    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

  48. [48]

    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

  49. [49]

    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

  50. [50]

    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

  51. [51]

    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

  52. [52]

    High-resolution image syn- thesis with latent diffusion models

    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj¨orn Ommer. High-resolution image syn- thesis with latent diffusion models. InCVPR, 2022. 3, 4, 6

    2022

  53. [53]

    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

  54. [54]

    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

  55. [55]

    Context- constrained hallucination for image super-resolution

    Jian Sun, Jiejie Zhu, and Marshall F Tappen. Context- constrained hallucination for image super-resolution. In CVPR, 2010. 1

    2010

  56. [56]

    Pixel-level and semantic-level adjustable super-resolution: A dual-lora approach

    Lingchen Sun, Rongyuan Wu, Zhiyuan Ma, Shuaizheng Liu, Qiaosi Yi, and Lei Zhang. Pixel-level and semantic-level adjustable super-resolution: A dual-lora approach. InCVPR,

  57. [57]

    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

  58. [58]

    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

  59. [59]

    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

  60. [60]

    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

  61. [61]

    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

  62. [62]

    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

  63. [63]

    Ex- ploring clip for assessing the look and feel of images

    Jianyi Wang, Kelvin CK Chan, and Chen Change Loy. Ex- ploring clip for assessing the look and feel of images. In AAAI, 2023. 2, 5, 6, 7

    2023

  64. [64]

    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

  65. [65]

    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

  66. [66]

    Esrgan: En- hanced super-resolution generative adversarial networks

    Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. Esrgan: En- hanced super-resolution generative adversarial networks. In ECCVW, 2018. 5

    2018

  67. [67]

    Real-esrgan: Training real-world blind super-resolution with pure synthetic data

    Xintao Wang, Liangbin Xie, Chao Dong, and Ying Shan. Real-esrgan: Training real-world blind super-resolution with pure synthetic data. InICCVW, 2021. 5, 7

    2021

  68. [68]

    Xintao Wang, Liangbin Xie, Ke Yu, Kelvin C. K. Chan, Chen Change Loy, and Chao Dong. Basicsr: Open source image and video restoration toolbox, 2022. GitHub reposi- tory. 5

    2022

  69. [69]

    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

  70. [70]

    Deep networks for image super-resolution with sparse prior

    Zhaowen Wang, Ding Liu, Jianchao Yang, Wei Han, and Thomas Huang. Deep networks for image super-resolution with sparse prior. InICCV, 2015. 2

    2015

  71. [71]

    One-step effective diffusion network for real-world image super-resolution

    Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, and Lei Zhang. One-step effective diffusion network for real-world image super-resolution. InNeurIPS, 2024. 3, 4, 5, 6

    2024

  72. [72]

    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. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 25456–25467, 2024. 2

    2024

  73. [73]

    arXiv preprint arXiv:2508.08227 (2025)

    Zhiqiang Wu, Zhaomang Sun, Tong Zhou, Bingtao Fu, Ji Cong, Yitong Dong, Huaqi Zhang, Xuan Tang, Mingsong Chen, and Xian Wei. Omgsr: You only need one mid- timestep guidance for real-world image super-resolution. arXiv preprint arXiv:2508.08227, 2025. 3, 6, 7

    work page arXiv 2025

  74. [74]

    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

  75. [75]

    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

  76. [76]

    Maniqa: Multi-dimension attention network for no-reference image quality assessment

    Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao, Yuan Gong, Mingdeng Cao, Jiahao Wang, and Yujiu Yang. Maniqa: Multi-dimension attention network for no-reference image quality assessment. InCVPRW, 2022. 2, 5, 6, 7

    2022

  77. [77]

    Pixel-aware stable diffusion for realistic image super- resolution and personalized stylization.arXiv preprint arXiv:2308.14469, 2023

    Tao Yang, Rongyuan Wu, Peiran Ren, Xuansong Xie, and Lei Zhang. Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization, 2023. arXiv preprint arXiv:2308.14469. 7

    work page arXiv 2023

  78. [78]

    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

  79. [79]

    Augment- ing perceptual super-resolution via image quality predictors

    Fengjia Zhang, Samrudhdhi B Rangrej, Tristan Aumentado- Armstrong, Afsaneh Fazly, and Alex Levinshtein. Augment- ing perceptual super-resolution via image quality predictors. InProceedings of the Computer Vision and Pattern Recogni- tion Conference, pages 2311–2322, 2025. 7

    2025

  80. [80]

    arXiv preprint arXiv:1701.05957 (2017)

    He Zhang, Vishwanath Sindagi, and Vishal M Patel. Im- age de-raining using a conditional generative adversarial net- work.arXiv preprint arXiv:1701.05957, 2017. 2

    work page arXiv 2017

Showing first 80 references.