Keywords: generative models, unsupervised learning
TL;DR: We present a novel framework to learn the disentangled representation of content and style in a completely unsupervised manner.
Abstract: It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation in a different and unpredictable way. It is rare for one to have access to a large number of data to help separate the influences. In this paper, we present a novel framework to learn this disentangled representation in a completely unsupervised manner. We address this problem in a two-branch Autoencoder framework. For the structural content branch, we project the latent factor into a soft structured point tensor and constrain it with losses derived from prior knowledge. This encourages the branch to distill geometry information. Another branch learns the complementary style information. The two branches form an effective framework that can disentangle object's content-style representation without any human annotation. We evaluate our approach on four image datasets, on which we demonstrate the superior disentanglement and visual analogy quality both in synthesized and real-world data. We are able to generate photo-realistic images with 256x256 resolution that are clearly disentangled in content and style.