Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
This addresses the issue of poor sample quality in autoencoders for image generation, though it appears incremental as it builds on existing AE and GAN methods.
The paper tackles the problem of generating blurry samples in autoencoders by introducing a GAN-based architecture that adversarially trains on latent space interpolations, resulting in non-blurry samples that match high- and low-level features of original images, with interpolations preserving realistic resemblances.
We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By using an AE as both the generator and discriminator of a GAN, we pass a pixel-wise error function across the discriminator, yielding an AE which produces non-blurry samples that match both high- and low-level features of the original images. Interpolations between images in this space remain within the latent-space distribution of real images as trained by the discriminator, and therfore preserve realistic resemblances to the network inputs. Code available at https://github.com/timsainb/GAIA