On the usage of visual saliency models for computer generated objects

Mona Abid (1, 2) , Matthieu Perreira da Silva (1, 2) , Patrick Le Callet (1, 2)

1 LS2N - Laboratoire des Sciences du Numérique de Nantes
2 LS2N - équipe IPI - Image Perception Interaction

Visual attention is a key feature to optimize visual experience of many multimedia applications. 2D visual attention computational modeling is an active research area considering the visualization of natural images on a conventional display. In this paper, we question the ability of such models to be applicable to single computer-generated objects rendered at different sizes (on a conventional display). We benchmark state of art visual attention models and investigate the influence of the viewpoint on those computational models applied on volumetric data and this to get a better understanding of how viewpoint information could be integrated into view-based approaches. To do so, a subjective experiment was conducted and a fine analysis was led using the variance analysis statistical method.

Mots clés: Index Terms-Visual attention models; perception; computer generated objects; computer vision

Domaines: Traitement des images [eess.IV]; Multimédia [cs.MM]

Mona Abid, Matthieu Perreira da Silva, Patrick Le Callet. On the usage of visual saliency models for computer generated objects. 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP), Sep 2019, Kuala Lumpur, Malaysia. pp.1-5, ⟨10.1109/MMSP.2019.8901782⟩. ⟨hal-02390900⟩