We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least approximately, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. On benchmarks, we demonstrate superior accuracy compared to another method that uses supervision at the level of 2D image correspondences.

中文翻译：

---

从野外图像中无监督学习可能对称的可变形 3D 对象


我们提出了一种从原始单视图图像中学习 3D 可变形对象类别的方法，无需外部监督。该方法基于自动编码器，将每个输入图像分解为深度、反照率、视点和照明。为了在没有监督的情况下解开这些组件，我们利用了许多对象类别至少近似具有对称结构的事实。我们表明，即使外观由于阴影而不对称，有关照明的推理也使我们能够利用潜在的对象对称性。此外，我们通过预测对称概率图来对可能但不一定对称的对象进行建模，并与模型的其他组件进行端到端学习。我们的实验表明，该方法可以从单视图图像中非常准确地恢复人脸、猫脸和汽车的 3D 形状，而无需任何监督或先验形状模型。在基准测试中，与另一种在 2D 图像对应级别使用监督的方法相比，我们展示了更高的准确性。