Data Interpolations in Deep Generative Models under Non-Simply-Connected Manifold Topology
Exploiting the deep generative model's remarkable ability of learning the data-manifold structure, some recent researches proposed a geometric data interpolation method based on the geodesic curves on the learned data-manifold. However, this interpolation method often gives poor results due to a topological difference between the model and the dataset. The model defines a family of simply-connected manifolds, whereas the dataset generally contains disconnected regions or holes that make them non-simply-connected. To compensate this difference, we propose a novel density regularizer that make the interpolation path circumvent the holes denoted by low probability density. We confirm that our method gives consistently better interpolation results from the experiments with real-world image datasets.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On Linear Interpolation in the Latent Space of Deep Generative Models
The underlying geometrical structure of the latent space in deep generative models is in most cases not Euclidean, which may lead to biases when comparing interpolation capabilities of two models. Smoothness and plausibi…
Discriminating Against Unrealistic Interpolations in Generative Adversarial Networks
Interpolations in the latent space of deep generative models is one of the standard tools to synthesize semantically meaningful mixtures of generated samples. As the generator function is non-linear, commonly used linear…
Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourages convex latent distributions
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 us…
Generative Adversarial NetworkDistribution-Interpolation Trade off in Generative Models
We investigate the properties of multidimensional probability distributions in the context of latent space prior distributions of implicit generative models. Our work revolves around the phenomena arising while decoding …
Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
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 us…
Generative Adversarial Network