Assessing Image Quality Using a Simple Generative Representation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909183855558656 |
|---|---|
| author | Raviv, Simon Chechik, Gal |
| author_facet | Raviv, Simon Chechik, Gal |
| contents | Perceptual image quality assessment (IQA) is the task of predicting the visual quality of an image as perceived by a human observer. Current state-of-the-art techniques are based on deep representations trained in discriminative manner. Such representations may ignore visually important features, if they are not predictive of class labels. Recent generative models successfully learn low-dimensional representations using auto-encoding and have been argued to preserve better visual features. Here we leverage existing auto-encoders and propose VAE-QA, a simple and efficient method for predicting image quality in the presence of a full-reference. We evaluate our approach on four standard benchmarks and find that it significantly improves generalization across datasets, has fewer trainable parameters, a smaller memory footprint and faster run time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18178 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Assessing Image Quality Using a Simple Generative Representation Raviv, Simon Chechik, Gal Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Graphics Machine Learning Perceptual image quality assessment (IQA) is the task of predicting the visual quality of an image as perceived by a human observer. Current state-of-the-art techniques are based on deep representations trained in discriminative manner. Such representations may ignore visually important features, if they are not predictive of class labels. Recent generative models successfully learn low-dimensional representations using auto-encoding and have been argued to preserve better visual features. Here we leverage existing auto-encoders and propose VAE-QA, a simple and efficient method for predicting image quality in the presence of a full-reference. We evaluate our approach on four standard benchmarks and find that it significantly improves generalization across datasets, has fewer trainable parameters, a smaller memory footprint and faster run time. |
| title | Assessing Image Quality Using a Simple Generative Representation |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2404.18178 |