Guiding Intelligent Surveillance System by learning-by-synthesis gaze estimation

TL;DR

This paper introduces a novel style transformation-based learning-by-synthesis approach for gaze estimation in surveillance systems, significantly improving synthetic image realism and model performance, reducing reliance on real data annotation.

Contribution

The paper proposes a new style transformation method to enhance synthetic image realism for gaze estimation, outperforming previous synthetic training approaches.

Findings

Generated images are highly realistic, confirmed by user studies.

Models trained on improved synthetic images outperform those trained on raw synthetic data.

Achieved state-of-the-art results on MPIIGaze and other datasets.

Abstract

We describe a novel learning-by-synthesis method for estimating gaze direction of an automated intelligent surveillance system. Recently, progress in learning-by-synthesis has proposed training models on synthetic images, which can effectively reduce the cost of manpower and material resources. However, learning from synthetic images still fails to achieve the desired performance compared to naturalistic images due to the different distribution of synthetic images. In an attempt to address this issue, previous method is to improve the realism of synthetic images by learning a model. However, the disadvantage of the method is that the distortion has not been improved and the authenticity level is unstable. To solve this problem, we put forward a new structure to improve synthetic images, via the reference to the idea of style transformation, through which we can efficiently reduce the distortion of pictures and minimize the need of real data annotation. We estimate that this enables generation of highly realistic images, which we demonstrate both qualitatively and with a user study. We quantitatively evaluate the generated images by training models for gaze estimation. We show a significant improvement over using synthetic images, and achieve state-of-the-art results on various datasets including MPIIGaze dataset.