Fixation prediction with a combined model of bottom-up saliency and vanishing point

TL;DR

This paper introduces a combined fixation prediction model that integrates bottom-up saliency with vanishing point information, demonstrating improved accuracy over existing models by incorporating scene structural cues.

Contribution

The study reveals the influence of vanishing points on gaze and develops a novel combined model that outperforms current saliency models in predicting human fixations.

Findings

Vanishing points attract human gaze in natural scenes.

The combined model outperforms state-of-the-art saliency models.

Inclusion of scene structure improves fixation prediction accuracy.

Abstract

By predicting where humans look in natural scenes, we can understand how they perceive complex natural scenes and prioritize information for further high-level visual processing. Several models have been proposed for this purpose, yet there is a gap between best existing saliency models and human performance. While many researchers have developed purely computational models for fixation prediction, less attempts have been made to discover cognitive factors that guide gaze. Here, we study the effect of a particular type of scene structural information, known as the vanishing point, and show that human gaze is attracted to the vanishing point regions. We record eye movements of 10 observers over 532 images, out of which 319 have vanishing points. We then construct a combined model of traditional saliency and a vanishing point channel and show that our model outperforms state of the art saliency models using three scores on our dataset.