论文标题
以对象为中心的图像生成具有分解的深度，位置和外观
Object-Centric Image Generation with Factored Depths, Locations, and Appearances
论文作者
论文摘要
我们提出了图像的生成模型，这些模型明确地推荐了它们显示的对象集。我们的模型学习了一个结构化的潜在表示，将对象与彼此和背景分开。与先前的作品不同，它明确表示每个对象的2D位置和深度，以及其分割面罩和外观的嵌入。该模型可以单独以纯粹无监督的方式从图像中训练，而无需对象面具或深度信息。此外，即使很大一部分训练图像包含遮挡，它始终会生成完整的对象。最后，我们表明我们的模型可以将新图像的分解分解为它们的组成对象，包括准确预测深度排序和遮挡部分的分割。
We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from each other and from the background; unlike prior works, it explicitly represents the 2D position and depth of each object, as well as an embedding of its segmentation mask and appearance. The model can be trained from images alone in a purely unsupervised fashion without the need for object masks or depth information. Moreover, it always generates complete objects, even though a significant fraction of training images contain occlusions. Finally, we show that our model can infer decompositions of novel images into their constituent objects, including accurate prediction of depth ordering and segmentation of occluded parts.
