Salvato in:
Dettagli Bibliografici
Autori principali: Wahba, Mahmoud Z. A., Barbato, Francesco, Baldoni, Sara, Battisti, Federica
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.04584
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912877319815168
author Wahba, Mahmoud Z. A.
Barbato, Francesco
Baldoni, Sara
Battisti, Federica
author_facet Wahba, Mahmoud Z. A.
Barbato, Francesco
Baldoni, Sara
Battisti, Federica
contents Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated Viewing Center Bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson Correlation Coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04584
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SalFormer360: a transformer-based saliency estimation model for 360-degree videos
Wahba, Mahmoud Z. A.
Barbato, Francesco
Baldoni, Sara
Battisti, Federica
Computer Vision and Pattern Recognition
Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated Viewing Center Bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson Correlation Coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.
title SalFormer360: a transformer-based saliency estimation model for 360-degree videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.04584