论文标题
自动链接：通过链接关键点来对人类骨骼和物体大纲进行自我监督的学习
AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints
论文作者
论文摘要
诸如关键点之类的结构化表示形式被广泛用于姿势转移，有条件的图像生成，动画和3D重建。但是，他们的监督学习需要每个目标域的昂贵注释。我们提出了一种自我监督的方法，该方法学会从外观上脱离对象结构，并用直边链接的2D关键点的图形。只有一个描绘同一对象类的图像集合，鉴于图像集合，都学习了关键点的位置及其成对边缘权重。所产生的图是可以解释的，例如，当应用于显示人的图像时，自动链接可恢复人类骨架拓扑。我们的关键成分是i）编码器，可以预测输入图像中的关键点位置，ii）共享图作为潜在变量，该图形在每个图像中链接了相同的对键点，iii）一个中间边缘图，将潜在图形边缘的权重和柔和的方式和IV的随机图像组合为in Inpaine thing Image thing Image tomask thepains tomask thepains tomask thepains tomask tomask fromeptime togement themend Magin。尽管更简单，但自动链接在已建立的关键点和构成估算基准和构造基准的基准和铺平的方式上的自动链接优于现有的自我监督方法，为在更多样化的数据集上的结构调节生成模型铺平了道路。项目网站：https：//xingzhehe.github.io/autolink/。
Structured representations such as keypoints are widely used in pose transfer, conditional image generation, animation, and 3D reconstruction. However, their supervised learning requires expensive annotation for each target domain. We propose a self-supervised method that learns to disentangle object structure from the appearance with a graph of 2D keypoints linked by straight edges. Both the keypoint location and their pairwise edge weights are learned, given only a collection of images depicting the same object class. The resulting graph is interpretable, for example, AutoLink recovers the human skeleton topology when applied to images showing people. Our key ingredients are i) an encoder that predicts keypoint locations in an input image, ii) a shared graph as a latent variable that links the same pairs of keypoints in every image, iii) an intermediate edge map that combines the latent graph edge weights and keypoint locations in a soft, differentiable manner, and iv) an inpainting objective on randomly masked images. Although simpler, AutoLink outperforms existing self-supervised methods on the established keypoint and pose estimation benchmarks and paves the way for structure-conditioned generative models on more diverse datasets. Project website: https://xingzhehe.github.io/autolink/.
