论文标题
通过平行生成对抗网络，以自我为中心的形象生成
Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
论文作者
论文摘要
最近已经提出了跨视图图像生成，以从另一个截然不同的视图中生成一个视图的图像。在本文中，我们研究了以自我为中心的（第三人称）观点（以自我为中心的（第一人称）查看图像生成。这是一项具有挑战性的任务，因为以自我为中心的观点有时与外向观点有很大不同。因此，转换两种视图的外观是一项非平凡的任务。为此，我们提出了一种新型的平行生成对抗网络（P-GAN），并具有新颖的交叉周期损失，以学习从外向视图中生成以自我为中心图像的共享信息。我们还将新颖的上下文特征丢失纳入学习过程中，以捕获图像中的上下文信息。 EXO-EGO数据集的大量实验表明，我们的模型的表现优于最先进的方法。
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.
