Generate High Resolution Images With Generative Variational Autoencoder
This work addresses image generation for computer vision applications, but it appears incremental as it modifies existing VAE and GAN components without a fundamental shift.
The authors tackled the problem of generating high-resolution images by introducing a novel neural network that replaces the VAE decoder with a discriminator, achieving state-of-the-art results on MNIST, LSUN, and CelebA datasets with improved sharpness and metrics like MMD and SSIM.
In this work, we present a novel neural network to generate high resolution images. We replace the decoder of VAE with a discriminator while using the encoder as it is. The encoder is fed data from a normal distribution while the generator is fed from a gaussian distribution. The combination from both is given to a discriminator which tells whether the generated image is correct or not. We evaluate our network on 3 different datasets: MNIST, LSUN and CelebA dataset. Our network beats the previous state of the art using MMD, SSIM, log likelihood, reconstruction error, ELBO and KL divergence as the evaluation metrics while generating much sharper images. This work is potentially very exciting as we are able to combine the advantages of generative models and inference models in a principled bayesian manner.