iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917027369713664 |
|---|---|
| author | Zhao, Zhaoran Yue, Xinli Sun, Jianhui Xie, Yuhao Shao, Tao Yao, Liangchao Xia, Fan Deng, Yuetang |
| author_facet | Zhao, Zhaoran Yue, Xinli Sun, Jianhui Xie, Yuhao Shao, Tao Yao, Liangchao Xia, Fan Deng, Yuetang |
| contents | Image Quality Assessment (IQA) has progressed from scalar quality prediction to more interpretable, human-aligned evaluation paradigms. In this work, we address the emerging challenge of detailed and explainable IQA by proposing iDETEX-a unified multimodal large language model (MLLM) capable of simultaneously performing three key tasks: quality grounding, perception, and description. To facilitate efficient and generalizable training across these heterogeneous subtasks, we design a suite of task-specific offline augmentation modules and a data mixing strategy. These are further complemented by online enhancement strategies to fully exploit multi-sourced supervision. We validate our approach on the large-scale ViDA-UGC benchmark, where iDETEX achieves state-of-the-art performance across all subtasks. Our model ranks first in the ICCV MIPI 2025 Detailed Image Quality Assessment Challenge, demonstrating its effectiveness and robustness in delivering accurate and interpretable quality assessments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17332 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA Zhao, Zhaoran Yue, Xinli Sun, Jianhui Xie, Yuhao Shao, Tao Yao, Liangchao Xia, Fan Deng, Yuetang Computer Vision and Pattern Recognition Image Quality Assessment (IQA) has progressed from scalar quality prediction to more interpretable, human-aligned evaluation paradigms. In this work, we address the emerging challenge of detailed and explainable IQA by proposing iDETEX-a unified multimodal large language model (MLLM) capable of simultaneously performing three key tasks: quality grounding, perception, and description. To facilitate efficient and generalizable training across these heterogeneous subtasks, we design a suite of task-specific offline augmentation modules and a data mixing strategy. These are further complemented by online enhancement strategies to fully exploit multi-sourced supervision. We validate our approach on the large-scale ViDA-UGC benchmark, where iDETEX achieves state-of-the-art performance across all subtasks. Our model ranks first in the ICCV MIPI 2025 Detailed Image Quality Assessment Challenge, demonstrating its effectiveness and robustness in delivering accurate and interpretable quality assessments. |
| title | iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.17332 |