Unpriortized Autoencoder For Image Generation
This addresses the problem of generating high-quality images in machine learning, but it appears incremental as it builds on existing autoencoder-based methods.
The paper tackles image generation by directly estimating the latent distribution in an autoencoder, rather than using a manually specified prior, and shows improved visual quality compared to previous autoencoder-based models.
In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assuming a manually specified prior, we approach the image generation task using an autoencoder by directly estimating the latent distribution. To this end, we introduce 'latent density estimator' which captures latent distribution explicitly and propose its structure. Through experiments, we show that our generative model generates images with the improved visual quality compared to previous autoencoder-based generative models.