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 $\beta$ of beta-VAE. Specifically, we reveal that the indistinguishability of decoder variance and $\beta$ hinders appropriate analysis of the model by random likelihood value, and limits performance improvement by omitting the gain from $\beta$. To address the problem, we propose Beta-Sigma VAE (BS-VAE) that explicitly separates $\beta$ and decoder variance $\sigma^2_x$ 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

本研究针对变分自编码器（VAE）输出模糊问题，提出了Beta-Sigma VAE（BS-VAE），该方法明确分离了模型中的beta和解码器方差，从而提高了自然图像合成的性能并提供了可控参数和可预测的分析。通过分析率-失真曲线和计算机视觉数据集的代理指标，我们的实验结果验证了该方法的有效性。

Beta-Sigma VAE：在高斯变分自编码器中分离beta和解码器方差