Deep Feature Consistent Variational Autoencoder

arXiv:1610.00291v2 Announce Type: replace
Abstract: We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent deep learning works such as style transfer, we employ a pre-trained deep convolutional neural …

abstract arxiv autoencoder consistent correlation cs.cv feature loss novel pixel spatial type vae