Multi‐exposure embeddings for graph learning: Towards high dynamic range image saliency prediction
| Title: | Multi‐exposure embeddings for graph learning: Towards high dynamic range image saliency prediction |
|---|---|
| Authors: | Jun Xing, Qiudan Zhang, Xuelin Shen, Xu Wang |
| Source: | IET Image Processing, Vol 18, Iss 6, Pp 1411-1421 (2024) |
| Publisher Information: | Wiley, 2024. |
| Publication Year: | 2024 |
| Collection: | LCC:Computer software |
| Subject Terms: | computer vision, image processing, multimedia databases, visual perception, Photography, TR1-1050, Computer software, QA76.75-76.765 |
| More Details: | Abstract Identifying saliency in high dynamic range (HDR) images is a fundamentally important issue in HDR imaging, and plays critical roles towards comprehensive scene understanding. Most of existing studies leverage hand‐crafted features for HDR image saliency prediction, lacking the capabilities of fully exploiting the characteristics of HDR image (i.e. wider luminance range and richer colour gamut). Here, systematical studies are carried out on HDR image saliency prediction by proposing a new framework to single out the contributions from multi‐exposure images. Specifically, inspired by the mechanism of HDR imaging, the method first utilizes graph neural networks to model the relations among multi‐exposure images and the tone‐mapped image obtained from an HDR image, enabling more discriminative saliency‐related feature representations. Subsequently, the saliency features driven by global semantic knowledge are aggregated from the tone‐mapped image through enhancing global context‐aware semantic information. Finally, a fusion module is designed to integrate saliency‐oriented feature representations originated from multi‐exposure images and the tone‐mapped image, producing the saliency maps of HDR images. Moreover, a new challenging HDR eye fixation database (HDR‐EYEFix) is created, expecting to further contribute the research on HDR image saliency prediction. Experiment results show that the method obtains superior performance compared to the state‐of‐the‐art methods. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 1751-9667 1751-9659 |
| Relation: | https://doaj.org/toc/1751-9659; https://doaj.org/toc/1751-9667 |
| DOI: | 10.1049/ipr2.13033 |
| Access URL: | https://doaj.org/article/0ece71cde216469facffd138c228466f |
| Accession Number: | edsdoj.0ece71cde216469facffd138c228466f |
| Database: | Directory of Open Access Journals |
| ISSN: | 17519667 17519659 |
|---|---|
| DOI: | 10.1049/ipr2.13033 |
| Published in: | IET Image Processing |
| Language: | English |