Super-resolution Variational Auto-Encoders
arXiv:2006.05218
Abstract
The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated images. Some studies link this effect to the objective function, namely, the (negative) log-likelihood. Here, we propose to enhance VAEs by adding a random variable that is a downscaled version of the original image and still use the log-likelihood function as the learning objective. Further, by providing the downscaled image as an input to the decoder, it can be used in a manner similar to the super-resolution. We present empirically that the proposed approach performs comparably to VAEs in terms of the negative log-likelihood, but it obtains a better FID score in data synthesis.
13 pages, 11 figures, 3 tables. Code available at: https://github.com/ioangatop/srVAE
References in corpus (11)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Conditional Image Generation with PixelCNN Decoders
- Density estimation using Real NVP
- Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
- Residual Flows for Invertible Generative Modeling
- Sylvester Normalizing Flows for Variational Inference
- Distribution Matching in Variational Inference
- Autoregressive Quantile Networks for Generative Modeling