论文标题
LitentKeyPointgan：通过潜在关键点控制图像 - 扩展摘要
LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract
论文作者
论文摘要
生成对抗网络（GAN）现在可以生成照片真实的图像。但是，如何最好地控制图像内容仍然是一个开放的挑战。我们介绍了LitentKeyPointGan，这是一个内部的两阶段gan，它在一组关键点和相关的外观嵌入式上，可控制生成的对象及其各自部件的位置和样式。我们解决的主要困难是将图像分解为几乎没有领域知识和监督信号的空间和外观因素。我们在一项用户研究和定量实验中证明了潜伏的潜在空间，可通过重新放置和交换关键点嵌入，例如通过将肖像结合在一起，并从不同的图像中使用肖像来重新安排生成的图像。值得注意的是，我们的方法不需要标签，因为它是自我监督的，因此适用于各种应用领域，例如编辑肖像，室内房间和全身人类姿势。
Generative adversarial networks (GANs) can now generate photo-realistic images. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN internally conditioned on a set of keypoints and associated appearance embeddings providing control of the position and style of the generated objects and their respective parts. A major difficulty that we address is disentangling the image into spatial and appearance factors with little domain knowledge and supervision signals. We demonstrate in a user study and quantitative experiments that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning and exchanging keypoint embeddings, such as generating portraits by combining the eyes, and mouth from different images. Notably, our method does not require labels as it is self-supervised and thereby applies to diverse application domains, such as editing portraits, indoor rooms, and full-body human poses.
