arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.06503cs.CV
收藏

Deforming Autoencoders:形状和外观的无监督解开

Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance

Stony Brook University(石溪大学);CentraleSupélec(高等电力学院);INRIA(法国国家信息与自动化研究所);Therapanacea;University College London(伦敦大学学院);Facebook AI Research(Facebook人工智能研究院)

Zhixin Shu, Mihir Sahasrabudhe, Alp Guler, Dimitris Samaras, Nikos Paragios, Iasonas Kokkinos

摘要:

在这项工作中,我们介绍了变形自动编码器,一个生成模型的图像,从外观中解开形状在一个无监督的方式。如在可变形模板范例中那样,形状被表示为规范坐标系(“模板”)和观察到的图像之间的变形,而外观在“规范”模板坐标中被建模,从而丢弃由于变形而引起的可变性。我们介绍了新的技术,允许这种方法被部署在自动编码器的设置,并表明这种方法可以用于无监督的组明智的图像对齐。我们展示了人类,手部和手指,面部操作,如形状和外观插值,以及无监督地标定位的表达变形实验。在模板坐标中,一种更强大的无监督解缠形式成为可能,使我们能够成功地将人脸图像分解为阴影和阴影,并进一步操作人脸图像。

英文摘要:

In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (`template') and an observed image, while appearance is modeled in `canonical', template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark localization. A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face images into shading and albedo, and further manipulate face images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑