IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

Huaibo Huang, zhihang li, Ran He, Zhenan Sun, Tieniu Tan

Neural Information Processing Systems 

We present a novel introspective variational autoencoder (IntroV AE) model for synthesizing high-resolution photographic images. IntroV AE is capable of self-evaluating the quality of its generated samples and improving itself accordingly. Its inference and generator models are jointly trained in an introspective way.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found