arxiv: 2604.10634 · v2 · submitted 2026-04-12 · 💻 cs.CV

Recognition: no theorem link

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

Abhishek Rajak, Alvaro Garcia Lara, Anas M. Ali, Anh-Kiet Duong, Ankit Kumar, Bangshu Xiong, Beibei Lin, Bihan Wen, Bilel Benjdira, Bingcai Wei, Bingchen Li, Bo Ding, Bowen Shao, Bowen Tie, Chang-De Peng, Changjian Wang, Chao Ren, Chieh-Yu Tsai, Chuan Chen, Chunlei Li, Cici Liu, Daniel Feijoo, Dimple Sonone, Diqi Chen, Enxuan Gu, Guan-Cheng Liu, Guanglu Dong, Guoyi Xu, Hao Yang, Heng Guo, Hongde Gu, Hongyuan Jing, Hui Geng, Huilin Zhao, Hui Zhang, Jean-Michel Carozza, Jiachen Tu, Jiangxin Dong, Jingxi Zhang, Jinshan Pan, Jun Chen, Junjun Jiang, Kele Xu, Kiran Raja, Kishor Upla, Kui Jiang, Lichao Mou, Li-Wei Kang, Li Yang, Liyuan Pan, Mache You, Marcos V. Conde, Mengmeng Zhang, Milan Kumar Singh, Mohab Kishawy, Paula Garrido Mellado, Peishu Shi, Petra Gomez-Kramer, Qiaofeng Ou, Qiaosi Yi, Qisheng Xu, Qiyao Zhao, Qiyu Rong, Radu Timofte, Robby T. Tan, Ruikun Zhang, Runzhe Li, Suhang Yao, Tianheng Zheng, Wadii Boulila, Wangzhi Xing, Wei Li, Wending Yan, Wenjie Li, Wenjing Xun, Xianming Liu, Xing Xu, Xin Jin, Xin Li, Xin Lu, Xuyao Deng, Yaokun Shi, Yaoxin Jiang, Yeming Lao, Yeying Jin, Yiang Chen, Yi Ren, Yufei Yang, Yu Li, Zeliang Li, Zhanyu Ma, Zhaocheng Yu, Zhaoxin Fan, Zhibo Chen, Zhibo Rao, Zhidong Zhu, Zida Zhang, Zongwei Wu

Authors on Pith no claims yet

Pith reviewed 2026-05-14 21:22 UTC · model grok-4.3

classification 💻 cs.CV

keywords raindrop removalimage restorationNTIRE challengedual-focused imagesday and night conditionsreal-world datasetcomputer vision benchmark

0 comments

The pith

The NTIRE 2026 challenge shows that submitted methods achieve strong performance on the Raindrop Clarity dataset for day and night raindrop removal in dual-focused images.

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

This paper gives an overview of the second NTIRE challenge focused on removing raindrops from images captured under day and night lighting with dual focus settings. It describes an updated real-world dataset called Raindrop Clarity that includes 14,139 training images, 407 validation images, and 593 test images. Out of 168 registered teams, 17 submitted valid solutions and fact sheets that performed strongly on the test set. The report frames these results as evidence of growing progress in the task. A reader would care because the challenge supplies a concrete benchmark for developing image restoration methods that work in practical outdoor conditions.

Core claim

The central claim is that the 17 submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating growing progress in raindrop removal under various illumination and focus conditions. The paper presents the adjusted dataset splits and the participation numbers as the basis for this conclusion, positioning the challenge as a practical benchmark for the field.

What carries the argument

The Raindrop Clarity dataset with its train, validation, and test splits functions as the evaluation benchmark that all submitted methods are measured against.

If this is right

The benchmark allows standardized comparison of future raindrop removal algorithms on the same real-world data.
Strong results support continued development of methods that handle combined illumination and focus variations.
The challenge format encourages broader participation in solving this specific image restoration problem.

Where Pith is reading between the lines

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

Methods successful on this dataset could be tested for generalization to other weather degradations such as fog or snow.
The dataset splits could be expanded with more varied scenes to check whether current performance holds outside the provided distribution.
Integration of these removal techniques into camera pipelines might reduce post-processing needs for outdoor photography.

Load-bearing premise

The adjusted Raindrop Clarity dataset with its specific train/validation/test splits sufficiently represents the full range of real-world day and night raindrop conditions on dual-focused images.

What would settle it

New dual-focused images collected independently under day and night rain conditions where the top challenge methods produce visibly incomplete raindrop removal or introduce new artifacts.

Figures

Figures reproduced from arXiv: 2604.10634 by Abhishek Rajak, Alvaro Garcia Lara, Anas M. Ali, Anh-Kiet Duong, Ankit Kumar, Bangshu Xiong, Beibei Lin, Bihan Wen, Bilel Benjdira, Bingcai Wei, Bingchen Li, Bo Ding, Bowen Shao, Bowen Tie, Chang-De Peng, Changjian Wang, Chao Ren, Chieh-Yu Tsai, Chuan Chen, Chunlei Li, Cici Liu, Daniel Feijoo, Dimple Sonone, Diqi Chen, Enxuan Gu, Guan-Cheng Liu, Guanglu Dong, Guoyi Xu, Hao Yang, Heng Guo, Hongde Gu, Hongyuan Jing, Hui Geng, Huilin Zhao, Hui Zhang, Jean-Michel Carozza, Jiachen Tu, Jiangxin Dong, Jingxi Zhang, Jinshan Pan, Jun Chen, Junjun Jiang, Kele Xu, Kiran Raja, Kishor Upla, Kui Jiang, Lichao Mou, Li-Wei Kang, Li Yang, Liyuan Pan, Mache You, Marcos V. Conde, Mengmeng Zhang, Milan Kumar Singh, Mohab Kishawy, Paula Garrido Mellado, Peishu Shi, Petra Gomez-Kramer, Qiaofeng Ou, Qiaosi Yi, Qisheng Xu, Qiyao Zhao, Qiyu Rong, Radu Timofte, Robby T. Tan, Ruikun Zhang, Runzhe Li, Suhang Yao, Tianheng Zheng, Wadii Boulila, Wangzhi Xing, Wei Li, Wending Yan, Wenjie Li, Wenjing Xun, Xianming Liu, Xing Xu, Xin Jin, Xin Li, Xin Lu, Xuyao Deng, Yaokun Shi, Yaoxin Jiang, Yeming Lao, Yeying Jin, Yiang Chen, Yi Ren, Yufei Yang, Yu Li, Zeliang Li, Zhanyu Ma, Zhaocheng Yu, Zhaoxin Fan, Zhibo Chen, Zhibo Rao, Zhidong Zhu, Zida Zhang, Zongwei Wu.

**Figure 2.** Figure 2: Method overview and qualitative results of Team raingod [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗

**Figure 4.** Figure 4: The pipeline of the method proposed by Team Retinex [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗

**Figure 6.** Figure 6: The pipeline of the method proposed by Team GU-day [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗

**Figure 7.** Figure 7: The pipeline of the method proposed by Team NTR [PITH_FULL_IMAGE:figures/full_fig_p007_7.png] view at source ↗

**Figure 8.** Figure 8: The pipeline of the method proposed by Team Cidaut AI [PITH_FULL_IMAGE:figures/full_fig_p007_8.png] view at source ↗

**Figure 9.** Figure 9: The pipeline of the method proposed by Team [PITH_FULL_IMAGE:figures/full_fig_p008_9.png] view at source ↗

**Figure 11.** Figure 11: The pipeline of the method proposed by Team MMAIri [PITH_FULL_IMAGE:figures/full_fig_p008_11.png] view at source ↗

**Figure 12.** Figure 12: The pipeline of the method proposed by Team Rain [PITH_FULL_IMAGE:figures/full_fig_p009_12.png] view at source ↗

**Figure 14.** Figure 14: The pipeline of the method proposed by Team PSU [PITH_FULL_IMAGE:figures/full_fig_p010_14.png] view at source ↗

**Figure 13.** Figure 13: The pipeline of the method proposed by Team Just JiT [PITH_FULL_IMAGE:figures/full_fig_p010_13.png] view at source ↗

**Figure 15.** Figure 15: The pipeline of the method proposed by Team [PITH_FULL_IMAGE:figures/full_fig_p011_15.png] view at source ↗

read the original abstract

This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this challenge attracted a wide range of impressive solutions, all developed and evaluated on our real-world Raindrop Clarity dataset~\cite{jin2024raindrop}. For this edition, we adjust the dataset with 14,139 images for training, 407 images for validation, and 593 images for testing. The primary goal of this challenge is to establish a strong and practical benchmark for the removal of raindrops under various illumination and focus conditions. In total, 168 teams have registered for the competition, and 17 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating the growing progress in this challenging task.

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.

Desk Editor's Note private letter to a colleague

This is a standard NTIRE challenge overview that updates the Raindrop Clarity dataset splits and reports 17 submissions but gives no quantitative results or analysis.

read the letter

This paper is the official summary for the second NTIRE challenge on day and night raindrop removal from dual-focused images. It updates the Raindrop Clarity dataset to 14,139 training images, 407 validation, and 593 test images, notes that 168 teams registered and 17 submitted valid solutions, and states that those solutions reached strong performance on the test set. The goal is framed as building a practical benchmark for real illumination and focus conditions that matter for applications like driving or surveillance. What the paper does well is simply documenting participation numbers and keeping the shared evaluation setup alive for the community. Challenge reports like this avoid the need for every new paper to re-create a testbed from scratch. The main limitation is that the text supplies no numbers, no baselines, no comparison to the first edition, and no error analysis. The claim of strong performance stays at the level of an assertion rather than evidence that can be checked from the document itself. If the full version includes tables and method summaries, that would change the picture, but the provided content does not. The representativeness of the 593-image test split for every possible real-world raindrop scenario is taken as given rather than demonstrated. This paper is mainly useful for people who track the NTIRE series or need the current benchmark numbers for context in their own deraining work. Readers hunting for new algorithms will have to turn to the individual team submissions instead. It shows clear, factual engagement with the task and the literature on image restoration, with no internal contradictions or invented claims. I would send it to peer review rather than desk reject it, because these challenge reports set the reference point for the field even when they are mostly descriptive.

Referee Report

1 major / 2 minor

Summary. This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. It describes adjustments to the Raindrop Clarity dataset (14,139 training images, 407 validation images, 593 test images), notes that 168 teams registered with 17 submitting valid final solutions and fact sheets, and states that the submitted methods achieved strong performance on the dataset, demonstrating progress in the task.

Significance. If the performance claims are substantiated, the paper is significant as a community benchmark report that documents participation and progress on real-world raindrop removal under varying illumination and focus conditions. Such challenge overviews help standardize evaluation and encourage development of practical restoration methods.

major comments (1)

Abstract: The central claim that 'the submitted methods achieved strong performance' is unsupported by any quantitative metrics (e.g., PSNR, SSIM), baseline comparisons, or error analysis. Without these, the assertion cannot be evaluated and is load-bearing for the paper's contribution as a challenge summary.

minor comments (2)

The dataset citation is given only as ~cite{jin2024raindrop}; the full bibliographic reference should be included in the reference list.
The term 'dual-focused images' is used without definition or explanation of how focus conditions are varied in the Raindrop Clarity dataset.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. We agree that the abstract requires quantitative support for the performance claim and will revise the manuscript accordingly to strengthen the presentation of results.

read point-by-point responses

Referee: Abstract: The central claim that 'the submitted methods achieved strong performance' is unsupported by any quantitative metrics (e.g., PSNR, SSIM), baseline comparisons, or error analysis. Without these, the assertion cannot be evaluated and is load-bearing for the paper's contribution as a challenge summary.

Authors: We agree that the abstract should be self-contained and include specific quantitative metrics. The full manuscript already reports detailed PSNR, SSIM, and other evaluation results for all 17 submitted methods in dedicated tables (with baseline comparisons), but these are not summarized in the abstract. In the revision we will add the top achieved PSNR and SSIM values, along with a brief note on the range of performance across submissions, directly into the abstract to substantiate the claim. revision: yes

Circularity Check

0 steps flagged

No significant circularity; factual challenge overview

full rationale

The paper is a standard NTIRE challenge report that states participation counts (168 registered, 17 valid submissions), dataset split sizes (14,139 train / 407 val / 593 test), and a high-level performance summary on the cited Raindrop Clarity benchmark. No derivations, equations, predictions, or load-bearing self-citations exist. The single dataset citation points to an external prior release and does not reduce any claim to a fitted input or self-definition. The central statement is scoped strictly to observed results on the supplied test set and contains no internal chain that collapses to its own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are introduced; the paper is an empirical challenge report that relies on an existing dataset and participant submissions.

pith-pipeline@v0.9.0 · 5867 in / 998 out tokens · 49617 ms · 2026-05-14T21:22:31.023462+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Reference graph

Works this paper leans on

95 extracted references · 95 canonical work pages · 1 internal anchor

[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. 3

work page 2026
[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. 3

work page 2026
[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,

work page 2026
[4]

Uav-rain1k: A benchmark for raindrop re- moval from uav aerial imagery

Wenhui Chang, Hongming Chen, Xin He, Xiang Chen, and Liangduo Shen. Uav-rain1k: A benchmark for raindrop re- moval from uav aerial imagery. InCVPR, pages 15–22,

work page
[5]

Re- thinking multi-scale representations in deep deraining trans- former

Hongming Chen, Xiang Chen, Jiyang Lu, and Yufeng Li. Re- thinking multi-scale representations in deep deraining trans- former. InAAAI, pages 1046–1053, 2024. 3, 4

work page 2024
[6]

Simple baselines for image restoration

Liangyu Chen, Xiaojie Chu, Xiangyu Zhang, and Jian Sun. Simple baselines for image restoration. InECCV, pages 17–

work page
[7]

Springer, 2022. 7, 9

work page 2022
[8]

Teaching tailored to talent: Adverse weather restoration via prompt pool and depth-anything con- straint

Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, and Lei Zhu. Teaching tailored to talent: Adverse weather restoration via prompt pool and depth-anything con- straint. InEuropean Conference on Computer Vision, pages 95–115. Springer, 2024. 2

work page 2024
[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...

work page 2026
[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. 3

work page 2026
[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. 3

work page 2026
[12]

Omni-kernel net- work for image restoration

Yuning Cui, Wenqi Ren, and Alois Knoll. Omni-kernel net- work for image restoration. InProceedings of the AAAI con- ference on artificial intelligence, pages 1426–1434, 2024. 9

work page 2024
[13]

Adair: Adaptive all-in-one image restoration via frequency mining and mod- ulation

Yuning Cui, Syed Waqas Zamir, Salman Khan, Alois Knoll, Mubarak Shah, and Fahad Shahbaz Khan. Adair: Adaptive all-in-one image restoration via frequency mining and mod- ulation. In13th international conference on learning rep- resentations, ICLR 2025, pages 57335–57356. ICLR, 2025. 6

work page 2025
[14]

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. 3

work page 2026
[15]

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. 3

work page 2026
[16]

Removing rain from single images via a deep detail network

Xueyang Fu, Jiabin Huang, Delu Zeng, Yue Huang, Xinghao Ding, and John Paisley. Removing rain from single images via a deep detail network. InProceedings of the IEEE con- ference on computer vision and pattern recognition, pages 3855–3863, 2017. 2

work page 2017
[17]

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. 3

work page 2026
[18]

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. 3

work page 2026
[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...

work page 2026
[20]

Learning from synthetic photorealistic raindrop for sin- gle image raindrop removal

Zhixiang Hao, Shaodi You, Yu Li, Kunming Li, and Feng Lu. Learning from synthetic photorealistic raindrop for sin- gle image raindrop removal. InICCV Workshops, pages 0–0,

work page
[21]

Masked autoencoders are scalable vision learners

Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll´ar, and Ross Girshick. Masked autoencoders are scalable vision learners. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000– 16009, 2022. 6

work page 2022
[22]

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. 3

work page 2026
[23]

Depth-attentional features for single-image rain removal

Xiaowei Hu, Chi-Wing Fu, Lei Zhu, and Pheng-Ann Heng. Depth-attentional features for single-image rain removal. In Proceedings of the IEEE/CVF Conference on computer vi- sion and pattern recognition, pages 8022–8031, 2019. 2

work page 2019
[24]

Multi-scale progressive fusion network for single image deraining

Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, and Junjun Jiang. Multi-scale progressive fusion network for single image deraining. In Proceedings of the IEEE/CVF conference on computer vi- sion and pattern recognition, pages 8346–8355, 2020. 2

work page 2020
[25]

Unsupervised night image enhancement: When layer decomposition meets light-effects suppression

Yeying Jin, Wenhan Yang, and Robby T Tan. Unsupervised night image enhancement: When layer decomposition meets light-effects suppression. InEuropean Conference on Com- puter Vision, pages 404–421. Springer, 2022. 2

work page 2022
[26]

Enhancing visibility in nighttime haze images using guided apsf and gradient adaptive convolution

Yeying Jin, Beibei Lin, Wending Yan, Yuan Yuan, Wei Ye, and Robby T Tan. Enhancing visibility in nighttime haze images using guided apsf and gradient adaptive convolution. InProceedings of the 31st ACM International Conference on Multimedia, pages 2446–2457, 2023. 2

work page 2023
[27]

Raindrop clarity: A dual-focused dataset for day and night raindrop removal

Yeying Jin, Xin Li, Jiadong Wang, Yan Zhang, and Malu Zhang. Raindrop clarity: A dual-focused dataset for day and night raindrop removal. InEuropean Conference on Com- puter Vision (ECCV), pages 1–17, 2024. 1, 2, 4

work page 2024
[28]

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...

work page 2026
[29]

Retinexdualv2: Physically- grounded dual retinex for generalized uhd image restoration,

Mohab Kishawy and Jun Chen. Retinexdualv2: Physically- grounded dual retinex for generalized uhd image restoration,

work page
[30]

Retinexdual: Retinex-based dual nature approach for gen- eralized ultra-high-definition image restoration, 2025

Mohab Kishawy, Ali Abdellatif Hussein, and Jun Chen. Retinexdual: Retinex-based dual nature approach for gen- eralized ultra-high-definition image restoration, 2025. 5

work page 2025
[31]

Hst: Hierarchical swin transformer for com- pressed image super-resolution

Bingchen Li, Xin Li, Yiting Lu, Sen Liu, Ruoyu Feng, and Zhibo Chen. Hst: Hierarchical swin transformer for com- pressed image super-resolution. InEuropean conference on computer vision, pages 651–668. Springer, 2022. 2

work page 2022
[32]

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. 3

work page 2026
[33]

Heavy rain image restoration: Integrating physics model and condi- tional adversarial learning

Ruoteng Li, Loong-Fah Cheong, and Robby T Tan. Heavy rain image restoration: Integrating physics model and condi- tional adversarial learning. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1633–1642, 2019. 2

work page 2019
[34]

Sin- gle image deraining: A comprehensive benchmark analysis

Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K Tokuda, Roberto Hirata Junior, Roberto Cesar- Junior, Jiawan Zhang, Xiaojie Guo, and Xiaochun Cao. Sin- gle image deraining: A comprehensive benchmark analysis. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3838–3847, 2019. 2

work page 2019
[35]

Back to Basics: Let Denoising Generative Models Denoise

Tianhong Li and Kaiming He. Back to basics: Let denoising generative models denoise.arXiv preprint arXiv:2511.13720, 2025. 10

work page internal anchor Pith review Pith/arXiv arXiv 2025
[36]

Learning disentangled fea- ture representation for hybrid-distorted image restoration

Xin Li, Xin Jin, Jianxin Lin, Sen Liu, Yaojun Wu, Tao Yu, Wei Zhou, and Zhibo Chen. Learning disentangled fea- ture representation for hybrid-distorted image restoration. In ECCV, pages 313–329. Springer, 2020. 2

work page 2020
[37]

Learning distortion invariant representation for image restoration from a causality perspective

Xin Li, Bingchen Li, Xin Jin, Cuiling Lan, and Zhibo Chen. Learning distortion invariant representation for image restoration from a causality perspective. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1714–1724, 2023. 2

work page 2023
[38]

Ntire 2025 challenge on day and night raindrop removal for dual-focused images: Methods and results

Xin Li, Yeying Jin, Xin Jin, Zongwei Wu, Bingchen Li, Yufei Wang, Wenhan Yang, Yu Li, Zhibo Chen, Bihan Wen, et al. Ntire 2025 challenge on day and night raindrop removal for dual-focused images: Methods and results. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 1172–1183, 2025. 2

work page 2025
[39]

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. 3

work page 2026
[40]

Rain streak removal using layer priors

Yu Li, Robby T Tan, Xiaojie Guo, Jiangbo Lu, and Michael S Brown. Rain streak removal using layer priors. InProceed- ings of the IEEE conference on computer vision and pattern recognition, pages 2736–2744, 2016. 2

work page 2016
[41]

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. InProceedings of the IEEE/CVF inter- national conference on computer vision, pages 1833–1844,

work page
[42]

Nighthaze: Nighttime image dehazing via self-prior learning.arXiv preprint arXiv:2403.07408, 2024

Beibei Lin, Yeying Jin, Wending Yan, Wei Ye, Yuan Yuan, and Robby T Tan. Nighthaze: Nighttime image dehazing via self-prior learning.arXiv preprint arXiv:2403.07408, 2024. 2

work page arXiv 2024
[43]

Nightrain: Nighttime video deraining via adaptive-rain-removal and adaptive-correction

Beibei Lin, Yeying Jin, Wending Yan, Wei Ye, Yuan Yuan, Shunli Zhang, and Robby T Tan. Nightrain: Nighttime video deraining via adaptive-rain-removal and adaptive-correction. InProceedings of the AAAI Conference on Artificial Intelli- gence, pages 3378–3385, 2024. 2

work page 2024
[44]

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. 3

work page 2026
[45]

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. 3

work page 2026
[46]

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...

work page 2026
[47]

A convnet for the 2020s.arXiv preprint arXiv:2201.03545, 2022

Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feicht- enhofer, Trevor Darrell, and Saining Xie. A convnet for the 2020s.arXiv preprint arXiv:2201.03545, 2022. 10

work page arXiv 2022
[48]

Aigc- vqa: A holistic perception metric for aigc video quality assessment

Yiting Lu, Xin Li, Bingchen Li, Zihao Yu, Fengbin Guan, Xinrui Wang, Ruling Liao, Yan Ye, and Zhibo Chen. Aigc- vqa: A holistic perception metric for aigc video quality assessment. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6384– 6394, 2024. 2

work page 2024
[49]

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. 3

work page 2026
[50]

Restoring vision in adverse weather conditions with patch-based denoising dif- fusion models.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8):10346–10357, 2023

Ozan ¨Ozdenizci and Robert Legenstein. Restoring vision in adverse weather conditions with patch-based denoising dif- fusion models.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8):10346–10357, 2023. 2

work page 2023
[51]

Fan: Frequency aggregation net- work for real image super-resolution

Yingxue Pang, Xin Li, Xin Jin, Yaojun Wu, Jianzhao Liu, Sen Liu, and Zhibo Chen. Fan: Frequency aggregation net- work for real image super-resolution. InComputer Vision– ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, pages 468–483. Springer, 2020. 2

work page 2020
[52]

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. 3

work page 2026
[53]

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. 3

work page 2026
[54]

I can see clearly now: Image restoration via de-raining

Horia Porav, Tom Bruls, and Paul Newman. I can see clearly now: Image restoration via de-raining. InICRA, pages 7087–

work page
[55]

Promptir: Prompting for all-in- one image restoration.Advances in Neural Information Pro- cessing Systems, 36:71275–71293, 2023

Vaishnav Potlapalli, Syed Waqas Zamir, Salman H Khan, and Fahad Shahbaz Khan. Promptir: Prompting for all-in- one image restoration.Advances in Neural Information Pro- cessing Systems, 36:71275–71293, 2023. 8

work page 2023
[56]

Attentive generative adversarial network for rain- drop removal from a single image

Rui Qian, Robby T Tan, Wenhan Yang, Jiajun Su, and Jiay- ing Liu. Attentive generative adversarial network for rain- drop removal from a single image. InProceedings of the IEEE conference on computer vision and pattern recogni- tion, pages 2482–2491, 2018. 1

work page 2018
[57]

Attentive generative adversarial network for rain- drop removal from a single image

Rui Qian, Robby T Tan, Wenhan Yang, Jiajun Su, and Jiay- ing Liu. Attentive generative adversarial network for rain- drop removal from a single image. InCVPR, pages 2482– 2491, 2018. 2

work page 2018
[58]

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. 3

work page 2026
[59]

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. 3

work page 2026
[60]

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. 3

work page 2026
[61]

Remov- ing raindrops and rain streaks in one go

Ruijie Quan, Xin Yu, Yuanzhi Liang, and Yi Yang. Remov- ing raindrops and rain streaks in one go. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9147–9156, 2021. 2

work page 2021
[62]

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. 3

work page 2026
[63]

STRRNet: Semantics-guided two-stage raindrop removal network

Qiyu Rong, Hongyuan Jing, Mengmeng Zhang, Jinlong Li, and Mengfei Han. STRRNet: Semantics-guided two-stage raindrop removal network. InCVPRW, 2025. 4

work page 2025
[64]

U- net: Convolutional networks for biomedical image segmen- tation

Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U- net: Convolutional networks for biomedical image segmen- tation. InMedical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pages 234–241. Springer, 2015. 5, 7, 10

work page 2015
[65]

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. 3

work page 2026
[66]

Rethinking real-world image deraining via an unpaired degradation-conditioned diffusion model.arXiv preprint arXiv:2301.09430, 2023

Yiyang Shen, Mingqiang Wei, Yongzhen Wang, Xueyang Fu, and Jing Qin. Rethinking real-world image deraining via an unpaired degradation-conditioned diffusion model.arXiv preprint arXiv:2301.09430, 2023. 2

work page arXiv 2023
[67]

Raindrops on windshield: Dataset and lightweight gradient-based detection algorithm

Vera Soboleva and Oleg Shipitko. Raindrops on windshield: Dataset and lightweight gradient-based detection algorithm. InIEEE SSCI, pages 1–7. IEEE, 2021. 2

work page 2021
[68]

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. 3

work page 2026
[69]

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...

work page 2026
[70]

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. 3

work page 2026
[71]

Restoring images in adverse weather condi- tions via histogram transformer

Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, and Xiaochun Cao. Restoring images in adverse weather condi- tions via histogram transformer. InECCV, pages 111–129. Springer, 2024. 3, 7

work page 2024
[72]

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, 10

work page 2016
[74]

Score-based self- supervised mri denoising.arXiv preprint arXiv:2505.05631,

Jiachen Tu, Yaokun Shi, and Fan Lam. Score-based self- supervised mri denoising.arXiv preprint arXiv:2505.05631,

work page arXiv
[75]

Maxim: Multi-axis mlp for image processing

Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, and Yinxiao Li. Maxim: Multi-axis mlp for image processing. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5769–5780, 2022. 2

work page 2022
[76]

Transweather: Transformer-based restoration of im- ages degraded by adverse weather conditions

Jeya Maria Jose Valanarasu, Rajeev Yasarla, and Vishal M Patel. Transweather: Transformer-based restoration of im- ages degraded by adverse weather conditions. InProceed- ings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2353–2363, 2022. 2

work page 2022
[77]

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. 3

work page 2026
[78]

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. 3

work page 2026
[79]

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. 3

work page 2026
[80]

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. 3

work page 2026
[81]

Spatial attentive single-image deraining with a high quality real rain dataset

Tianyu Wang, Xin Yang, Ke Xu, Shaozhe Chen, Qiang Zhang, and Rynson WH Lau. Spatial attentive single-image deraining with a high quality real rain dataset. InProceed- ings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12270–12279, 2019. 2

work page 2019

Showing first 80 references.