Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909252756439040 |
|---|---|
| author | You, Zhiyuan Li, Zheyuan Gu, Jinjin Yin, Zhenfei Xue, Tianfan Dong, Chao |
| author_facet | You, Zhiyuan Li, Zheyuan Gu, Jinjin Yin, Zhenfei Xue, Tianfan Dong, Chao |
| contents | We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods. DepictQA allows for detailed, language-based, human-like evaluation of image quality by leveraging Multi-modal Large Language Models (MLLMs). Unlike conventional Image Quality Assessment (IQA) methods relying on scores, DepictQA interprets image content and distortions descriptively and comparatively, aligning closely with humans' reasoning process. To build the DepictQA model, we establish a hierarchical task framework, and collect a multi-modal IQA training dataset. To tackle the challenges of limited training data and multi-image processing, we propose to use multi-source training data and specialized image tags. These designs result in a better performance of DepictQA than score-based approaches on multiple benchmarks. Moreover, compared with general MLLMs, DepictQA can generate more accurate reasoning descriptive languages. We also demonstrate that our full-reference dataset can be extended to non-reference applications. These results showcase the research potential of multi-modal IQA methods. Codes and datasets are available in https://depictqa.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_08962 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models You, Zhiyuan Li, Zheyuan Gu, Jinjin Yin, Zhenfei Xue, Tianfan Dong, Chao Computer Vision and Pattern Recognition We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods. DepictQA allows for detailed, language-based, human-like evaluation of image quality by leveraging Multi-modal Large Language Models (MLLMs). Unlike conventional Image Quality Assessment (IQA) methods relying on scores, DepictQA interprets image content and distortions descriptively and comparatively, aligning closely with humans' reasoning process. To build the DepictQA model, we establish a hierarchical task framework, and collect a multi-modal IQA training dataset. To tackle the challenges of limited training data and multi-image processing, we propose to use multi-source training data and specialized image tags. These designs result in a better performance of DepictQA than score-based approaches on multiple benchmarks. Moreover, compared with general MLLMs, DepictQA can generate more accurate reasoning descriptive languages. We also demonstrate that our full-reference dataset can be extended to non-reference applications. These results showcase the research potential of multi-modal IQA methods. Codes and datasets are available in https://depictqa.github.io. |
| title | Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.08962 |