Litcius/Paper detail

Visual ScanPath Transformer: Guiding Computers to See the World

Mengyu Qiu, Rong Quan, Dong Liang, Huawei Tu

202315 citationsDOI

Abstract

We propose to exploit the scanpath prediction technology to simulate human visual system to automatically generate gaze scanpaths for VR/AR applications, to alleviate the equipment and computational cost in foveated rendering. Specifically, we propose a novel deep learning-based scanpath prediction model called Visual ScanPath Transformer (VSPT), to predict human gaze scanpaths in both free viewing and task-driven viewing situations, based on which the VR/AR systems can execute foveated rendering rapidly and cheaply. The proposed VSPT first extracts highly task-related image features from the visual scene, and then explores the global dependency relationships among all the image regions to generate each image region a global feature. Next, VSPT simulates the human visual working memory to consider all the previous fixations’ influences when predicting each fixation. Experimental findings confirm that our model exhibits adherence to classical visual principles during saccadic decision-making, surpassing the current state-of-the-art performance in free-viewing and task-driven (goal-driven and question-driven) visual scenarios.

Topics & Concepts

Computer scienceGazeRendering (computer graphics)Artificial intelligenceExploitComputer visionVisualizationFixation (population genetics)Eye trackingSaccadic maskingEye movementHuman visual system modelImage (mathematics)Computer securitySociologyPopulationDemographyVisual Attention and Saliency DetectionGaze Tracking and Assistive TechnologyRetinal Imaging and Analysis
Visual ScanPath Transformer: Guiding Computers to See the World | Litcius