This paper addresses the unsupervised learning of content-style decompos...
Content and style (C-S) disentanglement intends to decompose the underly...
Disentangled generative models are typically trained with an extra
regul...
The key idea of the state-of-the-art VAE-based unsupervised representati...
We present a learning-based approach with pose perceptual loss for autom...