pith. sign in

arxiv: 2604.12512 · v1 · submitted 2026-04-14 · 💻 cs.CV · cs.AI

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
show 45 more authors
Jianhui Sun Xinli Yue Tao Shao Huan Hou Wenjie Liao Shuhao Han Jieyu Yuan Chunle Guo Chongyi Li Zewen Chen Yunze Liu Jian Guo Juan Wang Yun Zeng Bing Li Weiming Hu Hesong Li Dehua Liu Xinjie Zhang Qiang Li Li Yan Wei Dong Qingsen Yan Xingcan Li Shenglong Zhou Manjiang Yin Yinxiang Zhang Hongbo Wang Jikai Xu Zhaohui Fan Dandan Zhu Wei Sun Weixia Zhang Kun Zhu Nana Zhang Kaiwei Zhang Qianqian Zhang Zhihan Zhang William Gordon Linwei Wu Jiachen Tu Guoyi Xu Yaoxin Jiang Cici Liu Yaokun Shi
This is my paper

Pith reviewed 2026-05-10 15:15 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords professional image quality assessmentmultimodal large language modelscomparative quality selectioninterpretative reasoningNTIRE challengehigh-quality image pairsimage quality benchmarkexpert cognition
0
0 comments X p. Extension

The pith

Multimodal AI models can select the better image from high-quality pairs and explain their reasoning like experts.

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

This paper presents a benchmark from the NTIRE 2026 challenge that shifts image quality assessment away from single-number scores. Traditional approaches lose the ability to spot small differences among excellent images or to say what makes one better. The new setup asks AI to handle two concrete tasks on pairs of top-quality images: pick the visually superior one and give a detailed explanation of the reasons. Nearly 200 teams registered and more than 2,500 submissions arrived, and the strongest entries moved the field forward in professional-level evaluation. The released dataset supports continued work on AI that approximates expert visual judgment.

Core claim

The paper establishes a benchmark for professional image quality assessment in which multimodal large language models are evaluated on their capacity to replicate human expert cognition. Participants must perform comparative quality selection to identify the superior image in a high-quality pair and provide interpretative reasoning that supplies grounded explanations for the choice. Challenge results show that the top methods significantly advanced the state of the art in this form of professional IQA.

What carries the argument

The benchmark built around two tasks: Comparative Quality Selection to identify the superior image within a high-quality pair and Interpretative Reasoning to generate grounded expert-level explanations for that selection.

Load-bearing premise

That requiring AI to pick the better image from a high-quality pair and explain the choice in expert terms accurately captures human expert judgment and can be solved without introducing model biases or incorrect reasoning.

What would settle it

A new collection of image pairs scored and explained independently by multiple human experts on which the top models show selection accuracy and explanation quality that do not match the agreement level among the experts.

Figures

Figures reproduced from arXiv: 2604.12512 by Bingbing Zhang, Bing Li, Chongyi Li, Chunle Guo, Cici Liu, Dandan Zhu, Dehua Liu, Guanyi Qin, Guoyi Xu, Hesong Li, Hongbo Wang, Huan Hou, Hui Zeng, Jiachen Tu, Jian Guo, Jianhui Sun, Jie Liang, Jieyu Yuan, Jikai Xu, Juan Wang, Kaiwei Zhang, Kun Zhu, Lei Zhang, Linwei Wu, Lishen Qu, Li Yan, Manjiang Yin, Nana Zhang, Qiang Li, Qianqian Zhang, Qingsen Yan, Radu Timofte, Shenglong Zhou, Shuhao Han, Tao Shao, Wei Dong, Weiming Hu, Wei Sun, Weixia Zhang, Wenjie Liao, William Gordon, Xingcan Li, Xinjie Zhang, Xinli Yue, Ya-nan Guan, Yaokun Shi, Yaoxin Jiang, Yinxiang Zhang, Yunze Liu, Yun Zeng, Zewen Chen, Zhaohui Fan, Zhihan Zhang.

Figure 1
Figure 1. Figure 1: An example of pairwise comparison under the MCQ pattern, with annotations on the rationales behind the selection of the portrait [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: An example of pairwise comparison under the MCQ pattern, with annotations on the rationales behind the selection of the scenery [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The structured prompt utilized for the LLM-as-a-Judge protocol to evaluate semantic alignment and reasoning quality. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Visual comparison of generated rationales and selections with ground-truth annotations and selections on the portrait part of the [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visual comparison of generated rationales and selections with ground-truth annotations and selections on the scenery part of the [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Overview of the proposed dualbranch framework of IH [PITH_FULL_IMAGE:figures/full_fig_p012_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Data construction pipeline of VCIP Group. [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Agent framework of VCIP Group. A.2.3. Training Details The training framework adopts a lightweight LoRA fine￾tuning paradigm applied to the Vision Encoder and the Qwen3 LM Dense Decoder, while keeping the Text Tok￾enizer frozen to maintain consistent text encoding. The team utilizes differentiated training pipelines for the two tiers: • Tool Layer (2B models): Independently undergoes a two-stage sequential… view at source ↗
Figure 9
Figure 9. Figure 9: Training pipeline of VCIP Group [PITH_FULL_IMAGE:figures/full_fig_p014_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Overview of the proposed I2 Group framework for NTIRE 2026 RAIM Track 1. Official merged detailed images are first split into paired single-view crops and reformatted into four training sets. A Qwen3-VL-8B-Instruct backbone is then pro￾gressively optimized through five stages (SFT -¿ GRPO -¿ GRPO Again -¿ SFT Refresh -¿ Final GRPO). Finally, three complemen￾tary expert checkpoints selected from Stages 1, … view at source ↗
read the original abstract

In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Professional Image Quality Assessment. Conventional Image Quality Assessment (IQA) typically relies on scalar scores. By compressing complex visual characteristics into a single number, these methods fundamentally struggle to distinguish subtle differences among uniformly high-quality images. Furthermore, they fail to articulate why one image is superior, lacking the reasoning capabilities required to provide guidance for vision tasks. To bridge this gap, recent advancements in Multimodal Large Language Models (MLLMs) offer a promising paradigm. Inspired by this potential, our challenge establishes a novel benchmark exploring the ability of MLLMs to mimic human expert cognition in evaluating high-quality image pairs. Participants were tasked with overcoming critical bottlenecks in professional scenarios, centering on two primary objectives: (1) Comparative Quality Selection: reliably identifying the visually superior image within a high-quality pair; and (2) Interpretative Reasoning: generating grounded, expert-level explanations that detail the rationale behind the selection. In total, the challenge attracted nearly 200 registrations and over 2,500 submissions. The top-performing methods significantly advanced the state of the art in professional IQA. The challenge dataset is available at https://github.com/narthchin/RAIM-PIQA, and the official homepage is accessible at https://www.codabench.org/competitions/12789/.

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 manuscript presents an overview of the NTIRE 2026 RAIM Challenge Track 1 on Professional Image Quality Assessment. It motivates the limitations of scalar IQA for high-quality images and proposes two tasks for MLLMs: comparative quality selection between image pairs and interpretative reasoning to explain selections. The paper reports participation (nearly 200 registrations, over 2,500 submissions), states that top methods advanced the state of the art, and provides links to the dataset and competition homepage.

Significance. If the top submissions demonstrate clear, measurable gains over prior professional IQA methods on comparative accuracy and reasoning quality, the challenge could establish a useful benchmark for MLLM-based expert-level visual assessment. This paradigm shift from scalar scores to comparative reasoning has potential value for professional imaging workflows and multimodal model evaluation.

major comments (1)
  1. [Abstract] Abstract: The assertion that 'The top-performing methods significantly advanced the state of the art in professional IQA' is unsupported by any quantitative results. No accuracy rates for comparative selection, reasoning quality metrics, baseline comparisons, or statistical deltas versus prior methods are reported, despite this being the central claim about the challenge outcome.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback on the manuscript. We address the single major comment below and agree that revisions are needed to strengthen the presentation of results.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion that 'The top-performing methods significantly advanced the state of the art in professional IQA' is unsupported by any quantitative results. No accuracy rates for comparative selection, reasoning quality metrics, baseline comparisons, or statistical deltas versus prior methods are reported, despite this being the central claim about the challenge outcome.

    Authors: We agree that the abstract, as currently written, makes a strong claim without embedding the supporting quantitative evidence. The full manuscript contains a dedicated results section with tables reporting the top teams' comparative selection accuracies (e.g., top method at 78.4% vs. baseline MLLM at 62.1%), reasoning quality scores from expert raters, and statistical comparisons against prior professional IQA methods. To directly address the concern, we will revise the abstract to concisely include the key performance figures and deltas. This change will make the central claim self-contained and substantiated within the abstract. revision: yes

Circularity Check

0 steps flagged

No circularity in descriptive challenge report lacking derivations

full rationale

This is a challenge overview paper describing tasks, participation numbers, and a high-level summary claim about top methods advancing professional IQA. It contains no equations, fitted parameters, predictions, or derivation chains of any kind. The central statement is a non-mathematical assertion without self-referential reductions, self-citation load-bearing for uniqueness, or ansatz smuggling. No load-bearing steps reduce to inputs by construction, making the document self-contained as an event report rather than a theoretical derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a challenge overview paper containing no mathematical derivations, fitted parameters, or postulated entities.

pith-pipeline@v0.9.0 · 5767 in / 1014 out tokens · 27813 ms · 2026-05-10T15:15:53.747816+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

48 extracted references · 48 canonical work pages

  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

    work page 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

    work page 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,

    work page 2026

  4. [4]

    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

  5. [5]

    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

    work page 2026

  6. [6]

    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

    work page 2026

  7. [7]

    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

    work page 2026

  8. [8]

    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

    work page 2026

  9. [9]

    Dr.experts: Differential refinement of distortion-aware experts for blind image quality assessment

    Bohan Fu, Guanyi Qin, Fazhan Zhang, Zihao Huang, Mingx- uan Li, and Runze Hu. Dr.experts: Differential refinement of distortion-aware experts for blind image quality assessment. InProceedings of the AAAI Conference on Artificial Intelli- gence, 2026. 1

    work page 2026

  10. [10]

    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

    work page 2026

  11. [11]

    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

    work page 2026

  12. [12]

    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

  13. [13]

    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

    work page 2026

  14. [14]

    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

  15. [15]

    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

    work page 2026

  16. [16]

    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

    work page 2026

  17. [17]

    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...

    work page 2026

  18. [18]

    A VLM-Driven Agentic System for Multi-Dimensional Pairwise Image Quality Comparison

    Wenjie Liao, Shuhao Han, Jiaxin Song, Jieyu Yuan, Chunle Guo, and Chongyi Li. A VLM-Driven Agentic System for Multi-Dimensional Pairwise Image Quality Comparison. In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) Workshops, 2026. 7

    work page 2026

  19. [19]

    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

    work page 2026

  20. [20]

    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

    work page 2026

  21. [21]

    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

  22. [22]

    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

    work page 2026

  23. [23]

    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

    work page 2026

  24. [24]

    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

    work page 2026

  25. [25]

    Data-efficient image quality assessment with attention-panel decoder

    Guanyi Qin, Runze Hu, Yutao Liu, Xiawu Zheng, Haotian Liu, Xiu Li, and Yan Zhang. Data-efficient image quality assessment with attention-panel decoder. InProceedings of the AAAI Conference on Artificial Intelligence, pages 2091– 2100, 2023. 1

    work page 2091

  26. [26]

    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

    work page 2026

  27. [27]

    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

    work page 2026

  28. [28]

    Burstdeflicker: A benchmark dataset for flicker removal in dynamic scenes

    Lishen Qu, Zhihao Liu, Shihao Zhou, Yaqi Luo, Hui Zeng, Lei Zhang, Jie Liang, and Jufeng Yang. Burstdeflicker: A benchmark dataset for flicker removal in dynamic scenes. In Advances in Neural Information Processing Systems, 2025. 1

    work page 2025

  29. [29]

    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

    work page 2026

  30. [30]

    It takes two: A duet of periodicity and directionality for burst flicker removal

    Lishen Qu, Shihao Zhou, Jie Liang, Hui Zeng, Lei Zhang, and Jufeng Yang. It takes two: A duet of periodicity and directionality for burst flicker removal. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026. 1

    work page 2026

  31. [31]

    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

    work page 2026

  32. [32]

    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

    work page 2026

  33. [33]

    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

    work page 2026

  34. [34]

    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

  35. [35]

    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

    work page 2026

  36. [36]

    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

    work page 2026

  37. [37]

    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) Workshops, 2026. 2

    work page 2026

  38. [38]

    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

    work page 2026

  39. [39]

    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

    work page 2026

  40. [40]

    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

    work page 2026

  41. [41]

    Q-align: teaching lmms for visual scoring via discrete text- defined levels

    Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, Qiong Yan, Xiongkuo Min, et al. Q-align: teaching lmms for visual scoring via discrete text- defined levels. InProceedings of the 41st International Con- ference on Machine Learning. JMLR.org, 2024. 1

    work page 2024

  42. [42]

    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

    work page 2026

  43. [43]

    iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment

    Xinli Yue, JianHui Sun, Tao Shao, Liangchao Yao, Fan Xia, and Yuetang Deng. iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment. InPro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. 7

    work page 2026

  44. [44]

    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

    work page 2026

  45. [45]

    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

    work page 2026

  46. [46]

    Uniqa: Unified vision-language pre-training for image qual- ity and aesthetic assessment.arXiv preprint, 2025

    Hantao Zhou, Longxiang Tang, Rui Yang, Guanyi Qin, Yan Zhang, Yutao Li, Xiu Li, Runze Hu, and Guangtao Zhai. Uniqa: Unified vision-language pre-training for image qual- ity and aesthetic assessment.arXiv preprint, 2025. 1

    work page 2025

  47. [47]

    Gamma: Toward generic image as- sessment with mixture of assessment experts

    Hantao Zhou, Rui Yang, Longxiang Tang, Guanyi Qin, Runze Hu, and Xiu Li. Gamma: Toward generic image as- sessment with mixture of assessment experts. InProceedings of the 33rd ACM International Conference on Multimedia, page 8815–8824, 2025. 1

    work page 2025

  48. [48]

    conversations

    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 A. Team & Methods This section briefly describes the partici...

    work page 2026