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.
Neural Information Processing Systems
Nov-20-2025, 14:13:51 GMT