Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.30269 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911728642555904 |
|---|---|
| author | Wang, Zhongling Zhou, Raymond Athar, Shahrukh Yang, Wenbo Wang, Zhou |
| author_facet | Wang, Zhongling Zhou, Raymond Athar, Shahrukh Yang, Wenbo Wang, Zhou |
| contents | Over the past decades, numerous Image Quality Assessment (IQA) models have emerged, aiming to predict the perceptual quality of images. However, individual models are often biased toward certain types of image content or distortions, depending on the design principle and process. An intuitive idea is to harness the strengths and mitigate the weaknesses of each IQA model, by fusing the scores of multiple models into a stronger one. Here we make one of the first attempts to seek an optimal solution for the idea and propose a general framework for unsupervised IQA score fusion using deep Maximum a Posteriori (MAP) estimation. The proposed model conducts fine-grained uncertainty estimation at the score level to increase the accuracy and reduce the uncertainty in fused predictions. Comprehensive experiments demonstrate the superiority of the proposed model over individual IQA models and other fusion methods. It also exhibits an interesting capability of rejecting ``bad" models in the fusion process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30269 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation Wang, Zhongling Zhou, Raymond Athar, Shahrukh Yang, Wenbo Wang, Zhou Computer Vision and Pattern Recognition Image and Video Processing Over the past decades, numerous Image Quality Assessment (IQA) models have emerged, aiming to predict the perceptual quality of images. However, individual models are often biased toward certain types of image content or distortions, depending on the design principle and process. An intuitive idea is to harness the strengths and mitigate the weaknesses of each IQA model, by fusing the scores of multiple models into a stronger one. Here we make one of the first attempts to seek an optimal solution for the idea and propose a general framework for unsupervised IQA score fusion using deep Maximum a Posteriori (MAP) estimation. The proposed model conducts fine-grained uncertainty estimation at the score level to increase the accuracy and reduce the uncertainty in fused predictions. Comprehensive experiments demonstrate the superiority of the proposed model over individual IQA models and other fusion methods. It also exhibits an interesting capability of rejecting ``bad" models in the fusion process. |
| title | Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2605.30269 |