Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911644885450752 |
|---|---|
| author | Khan, Fadeel Sher Le, Long N. Venkataramanan, Abhinau K. Lee, Seok-Jun Sheikh, Hamid R. |
| author_facet | Khan, Fadeel Sher Le, Long N. Venkataramanan, Abhinau K. Lee, Seok-Jun Sheikh, Hamid R. |
| contents | Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable, localized feedback on specific image distortions. We overcome these limitations by shifting from absolute quality prediction to a relational and directional assessment. Our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02863 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions Khan, Fadeel Sher Le, Long N. Venkataramanan, Abhinau K. Lee, Seok-Jun Sheikh, Hamid R. Computer Vision and Pattern Recognition Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable, localized feedback on specific image distortions. We overcome these limitations by shifting from absolute quality prediction to a relational and directional assessment. Our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores. |
| title | Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.02863 |