Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
This work addresses a specific cross-view image generation problem in computer vision, with incremental improvements over existing methods.
The paper tackles the challenging task of generating egocentric (first-person) images from exocentric (third-person) views by proposing a Parallel Generative Adversarial Network (P-GAN) with cross-cycle and contextual feature losses, achieving state-of-the-art performance on the Exo-Ego datasets.
Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate exocentric (third-person) view to egocentric (first-person) 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 show that our model outperforms the state-of-the-art approaches.