Beta-Sigma VAE: Separating beta and decoder variance in Gaussian variational autoencoder
This addresses a known bottleneck in generative models for computer vision, offering incremental improvements in clarity and analysis.
The paper tackles the blurry output problem in variational autoencoders by proposing Beta-Sigma VAE, which separates beta and decoder variance, resulting in superior performance in natural image synthesis and controllable parameters.
Variational autoencoder (VAE) is an established generative model but is notorious for its blurriness. In this work, we investigate the blurry output problem of VAE and resolve it, exploiting the variance of Gaussian decoder and $β$ of beta-VAE. Specifically, we reveal that the indistinguishability of decoder variance and $β$ hinders appropriate analysis of the model by random likelihood value, and limits performance improvement by omitting the gain from $β$. To address the problem, we propose Beta-Sigma VAE (BS-VAE) that explicitly separates $β$ and decoder variance $σ^2_x$ in the model. Our method demonstrates not only superior performance in natural image synthesis but also controllable parameters and predictable analysis compared to conventional VAE. In our experimental evaluation, we employ the analysis of rate-distortion curve and proxy metrics on computer vision datasets. The code is available on https://github.com/overnap/BS-VAE