Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.12512 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908962539962368 |
|---|---|
| author | Qin, Guanyi Liang, Jie Zhang, Bingbing Qu, Lishen Guan, Ya-nan Zeng, Hui Zhang, Lei Timofte, Radu Sun, Jianhui Yue, Xinli Shao, Tao Hou, Huan Liao, Wenjie Han, Shuhao Yuan, Jieyu Guo, Chunle Li, Chongyi Chen, Zewen Liu, Yunze Guo, Jian Wang, Juan Zeng, Yun Li, Bing Hu, Weiming Li, Hesong Liu, Dehua Zhang, Xinjie Li, Qiang Yan, Li Dong, Wei Yan, Qingsen Li, Xingcan Zhou, Shenglong Yin, Manjiang Zhang, Yinxiang Wang, Hongbo Xu, Jikai Fan, Zhaohui Zhu, Dandan Sun, Wei Zhang, Weixia Zhu, Kun Zhang, Nana Zhang, Kaiwei Zhang, Qianqian Zhang, Zhihan Gordon, William Wu, Linwei Tu, Jiachen Xu, Guoyi Jiang, Yaoxin Liu, Cici Shi, Yaokun |
| author_facet | Qin, Guanyi Liang, Jie Zhang, Bingbing Qu, Lishen Guan, Ya-nan Zeng, Hui Zhang, Lei Timofte, Radu Sun, Jianhui Yue, Xinli Shao, Tao Hou, Huan Liao, Wenjie Han, Shuhao Yuan, Jieyu Guo, Chunle Li, Chongyi Chen, Zewen Liu, Yunze Guo, Jian Wang, Juan Zeng, Yun Li, Bing Hu, Weiming Li, Hesong Liu, Dehua Zhang, Xinjie Li, Qiang Yan, Li Dong, Wei Yan, Qingsen Li, Xingcan Zhou, Shenglong Yin, Manjiang Zhang, Yinxiang Wang, Hongbo Xu, Jikai Fan, Zhaohui Zhu, Dandan Sun, Wei Zhang, Weixia Zhu, Kun Zhang, Nana Zhang, Kaiwei Zhang, Qianqian Zhang, Zhihan Gordon, William Wu, Linwei Tu, Jiachen Xu, Guoyi Jiang, Yaoxin Liu, Cici Shi, Yaokun |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12512 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1) Qin, Guanyi Liang, Jie Zhang, Bingbing Qu, Lishen Guan, Ya-nan Zeng, Hui Zhang, Lei Timofte, Radu Sun, Jianhui Yue, Xinli Shao, Tao Hou, Huan Liao, Wenjie Han, Shuhao Yuan, Jieyu Guo, Chunle Li, Chongyi Chen, Zewen Liu, Yunze Guo, Jian Wang, Juan Zeng, Yun Li, Bing Hu, Weiming Li, Hesong Liu, Dehua Zhang, Xinjie Li, Qiang Yan, Li Dong, Wei Yan, Qingsen Li, Xingcan Zhou, Shenglong Yin, Manjiang Zhang, Yinxiang Wang, Hongbo Xu, Jikai Fan, Zhaohui Zhu, Dandan Sun, Wei Zhang, Weixia Zhu, Kun Zhang, Nana Zhang, Kaiwei Zhang, Qianqian Zhang, Zhihan Gordon, William Wu, Linwei Tu, Jiachen Xu, Guoyi Jiang, Yaoxin Liu, Cici Shi, Yaokun Computer Vision and Pattern Recognition Artificial Intelligence 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/. |
| title | NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1) |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.12512 |