论文标题
Insetgan用于全身图像生成
InsetGAN for Full-Body Image Generation
论文作者
论文摘要
尽管甘恩可以在某些领域的理想条件下产生照片现实的图像，但由于身份，发型，衣服和姿势方差的多样性，全身人类图像的产生仍然很困难。我们没有用单个gan对这个复杂的结构域进行建模，而是提出了一种新颖的方法来结合多个牙齿的甘体，其中一个gan产生了全球画布（例如，人体）和一组专门的甘套或插图，专注于不同的部分（例如，面部，鞋子，鞋子），可以无缝地插入全球帆布上。我们将问题建模为共同探索各自的潜在空间，以便可以通过将专用发电机的零件插入全局帆布，而无需引入接缝，从而可以组合生成的图像。我们通过将全身gan与专用的高质量脸部结合以产生合理的人类来演示设置。我们通过定量指标和用户研究评估结果。
While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. Instead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas. We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams. We demonstrate the setup by combining a full body GAN with a dedicated high-quality face GAN to produce plausible-looking humans. We evaluate our results with quantitative metrics and user studies.
