Content-Distortion High-Order Interaction for Blind Image Quality Assessment
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_ | 1866910905442238464 |
|---|---|
| author | Liu, Shuai Mao, Qingyu Li, Chao Chen, Jiacong Meng, Fanyang Tian, Yonghong Liang, Yongsheng |
| author_facet | Liu, Shuai Mao, Qingyu Li, Chao Chen, Jiacong Meng, Fanyang Tian, Yonghong Liang, Yongsheng |
| contents | The content and distortion are widely recognized as the two primary factors affecting the visual quality of an image. While existing No-Reference Image Quality Assessment (NR-IQA) methods have modeled these factors, they fail to capture the complex interactions between content and distortions. This shortfall impairs their ability to accurately perceive quality. To confront this, we analyze the key properties required for interaction modeling and propose a robust NR-IQA approach termed CoDI-IQA (Content-Distortion high-order Interaction for NR-IQA), which aggregates local distortion and global content features within a hierarchical interaction framework. Specifically, a Progressive Perception Interaction Module (PPIM) is proposed to explicitly simulate how content and distortions independently and jointly influence image quality. By integrating internal interaction, coarse interaction, and fine interaction, it achieves high-order interaction modeling that allows the model to properly represent the underlying interaction patterns. To ensure sufficient interaction, multiple PPIMs are employed to hierarchically fuse multi-level content and distortion features at different granularities. We also tailor a training strategy suited for CoDI-IQA to maintain interaction stability. Extensive experiments demonstrate that the proposed method notably outperforms the state-of-the-art methods in terms of prediction accuracy, data efficiency, and generalization ability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05076 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Content-Distortion High-Order Interaction for Blind Image Quality Assessment Liu, Shuai Mao, Qingyu Li, Chao Chen, Jiacong Meng, Fanyang Tian, Yonghong Liang, Yongsheng Computer Vision and Pattern Recognition The content and distortion are widely recognized as the two primary factors affecting the visual quality of an image. While existing No-Reference Image Quality Assessment (NR-IQA) methods have modeled these factors, they fail to capture the complex interactions between content and distortions. This shortfall impairs their ability to accurately perceive quality. To confront this, we analyze the key properties required for interaction modeling and propose a robust NR-IQA approach termed CoDI-IQA (Content-Distortion high-order Interaction for NR-IQA), which aggregates local distortion and global content features within a hierarchical interaction framework. Specifically, a Progressive Perception Interaction Module (PPIM) is proposed to explicitly simulate how content and distortions independently and jointly influence image quality. By integrating internal interaction, coarse interaction, and fine interaction, it achieves high-order interaction modeling that allows the model to properly represent the underlying interaction patterns. To ensure sufficient interaction, multiple PPIMs are employed to hierarchically fuse multi-level content and distortion features at different granularities. We also tailor a training strategy suited for CoDI-IQA to maintain interaction stability. Extensive experiments demonstrate that the proposed method notably outperforms the state-of-the-art methods in terms of prediction accuracy, data efficiency, and generalization ability. |
| title | Content-Distortion High-Order Interaction for Blind Image Quality Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05076 |