MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
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_ | 1866911118583136256 |
|---|---|
| author | Yao, Shunyu Liu, Ming Zhang, Zhilu Wan, Zhaolin Ji, Zhilong Bai, Jinfeng Zuo, Wangmeng |
| author_facet | Yao, Shunyu Liu, Ming Zhang, Zhilu Wan, Zhaolin Ji, Zhilong Bai, Jinfeng Zuo, Wangmeng |
| contents | Recent advancements in image quality assessment (IQA), driven by sophisticated deep neural network designs, have significantly improved the ability to approach human perceptions. However, most existing methods are obsessed with fitting the overall score, neglecting the fact that humans typically evaluate image quality from different dimensions before arriving at an overall quality assessment. To overcome this problem, we propose a multi-dimensional image quality assessment (MDIQA) framework. Specifically, we model image quality across various perceptual dimensions, including five technical and four aesthetic dimensions, to capture the multifaceted nature of human visual perception within distinct branches. Each branch of our MDIQA is initially trained under the guidance of a separate dimension, and the respective features are then amalgamated to generate the final IQA score. Additionally, when the MDIQA model is ready, we can deploy it for a flexible training of image restoration (IR) models, enabling the restoration results to better align with varying user preferences through the adjustment of perceptual dimension weights. Extensive experiments demonstrate that our MDIQA achieves superior performance and can be effectively and flexibly applied to image restoration tasks. The code is available: https://github.com/YaoShunyu19/MDIQA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16887 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration Yao, Shunyu Liu, Ming Zhang, Zhilu Wan, Zhaolin Ji, Zhilong Bai, Jinfeng Zuo, Wangmeng Computer Vision and Pattern Recognition Image and Video Processing Recent advancements in image quality assessment (IQA), driven by sophisticated deep neural network designs, have significantly improved the ability to approach human perceptions. However, most existing methods are obsessed with fitting the overall score, neglecting the fact that humans typically evaluate image quality from different dimensions before arriving at an overall quality assessment. To overcome this problem, we propose a multi-dimensional image quality assessment (MDIQA) framework. Specifically, we model image quality across various perceptual dimensions, including five technical and four aesthetic dimensions, to capture the multifaceted nature of human visual perception within distinct branches. Each branch of our MDIQA is initially trained under the guidance of a separate dimension, and the respective features are then amalgamated to generate the final IQA score. Additionally, when the MDIQA model is ready, we can deploy it for a flexible training of image restoration (IR) models, enabling the restoration results to better align with varying user preferences through the adjustment of perceptual dimension weights. Extensive experiments demonstrate that our MDIQA achieves superior performance and can be effectively and flexibly applied to image restoration tasks. The code is available: https://github.com/YaoShunyu19/MDIQA. |
| title | MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2508.16887 |