Parallel Generative Adversarial Network for Third-person to First-person Image Generation

Abstract

Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate third-person (exocentric) view to first-person (egocentric) view image generation. This is a challenging task since egocentric view sometimes is remarkably different from exocentric view. Thus, transforming the appearances across the two views is a non-trivial task. To this end, we propose a novel Parallel Generative Adversarial Network (P-GAN) with a novel cross-cycle loss to learn the shared information for generating egocentric images from exocentric view. We also incorporate a novel contextual feature loss in the learning procedure to capture the contextual information in images. Extensive experiments on the Exo-Ego datasets [5] show that our model outperforms the state-of-the-art approaches.