Bridging the Gap Between Saliency Prediction and Image Quality Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911026334662656 |
|---|---|
| author | Alexey, Kirillov Moskalenko, Andrey Vatolin, Dmitriy |
| author_facet | Alexey, Kirillov Moskalenko, Andrey Vatolin, Dmitriy |
| contents | Over the past few years, deep neural models have made considerable advances in image quality assessment (IQA). However, the underlying reasons for their success remain unclear, owing to the complex nature of deep neural networks. IQA aims to describe how the human visual system (HVS) works and to create its efficient approximations. On the other hand, Saliency Prediction task aims to emulate HVS via determining areas of visual interest. Thus, we believe that saliency plays a crucial role in human perception. In this work, we conduct an empirical study that reveals the relation between IQA and Saliency Prediction tasks, demonstrating that the former incorporates knowledge of the latter. Moreover, we introduce a novel SACID dataset of saliency-aware compressed images and conduct a large-scale comparison of classic and neural-based IQA methods. All supplementary code and data will be available at the time of publication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04997 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bridging the Gap Between Saliency Prediction and Image Quality Assessment Alexey, Kirillov Moskalenko, Andrey Vatolin, Dmitriy Computer Vision and Pattern Recognition Image and Video Processing Over the past few years, deep neural models have made considerable advances in image quality assessment (IQA). However, the underlying reasons for their success remain unclear, owing to the complex nature of deep neural networks. IQA aims to describe how the human visual system (HVS) works and to create its efficient approximations. On the other hand, Saliency Prediction task aims to emulate HVS via determining areas of visual interest. Thus, we believe that saliency plays a crucial role in human perception. In this work, we conduct an empirical study that reveals the relation between IQA and Saliency Prediction tasks, demonstrating that the former incorporates knowledge of the latter. Moreover, we introduce a novel SACID dataset of saliency-aware compressed images and conduct a large-scale comparison of classic and neural-based IQA methods. All supplementary code and data will be available at the time of publication. |
| title | Bridging the Gap Between Saliency Prediction and Image Quality Assessment |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2405.04997 |