Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space

• URL: http://arxiv.org/abs/2009.06529v1
• Date: Mon, 14 Sep 2020 15:45:58 GMT
• Title: Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
• Authors: Jonas Wulff and Antonio Torralba
• Abstract summary: Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. We show that, under a simple nonlinear operation, the data distribution can be modeled as Gaussian and therefore expressed using sufficient statistics. The resulting projections lie in smoother and better behaved regions of the latent space, as shown using performance for both real and generated images.
• Score: 41.20193123974535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. It has been shown that a wide range of images can be projected into this space, including images outside of the domain that the generator was trained on. However, while in this case the generator reproduces the pixels and textures of the images, the reconstructed latent vectors are unstable and small perturbations result in significant image distortions. In this work, we propose to explicitly model the data distribution in latent space. We show that, under a simple nonlinear operation, the data distribution can be modeled as Gaussian and therefore expressed using sufficient statistics. This yields a simple Gaussian prior, which we use to regularize the projection of images into the latent space. The resulting projections lie in smoother and better behaved regions of the latent space, as shown using interpolation performance for both real and generated images. Furthermore, the Gaussian model of the distribution in latent space allows us to investigate the origins of artifacts in the generator output, and provides a method for reducing these artifacts while maintaining diversity of the generated images.

Related papers

• L3DG: Latent 3D Gaussian Diffusion [74.36431175937285]
  L3DG is the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. We employ a sparse convolutional architecture to efficiently operate on room-scale scenes. By leveraging the 3D Gaussian representation, the generated scenes can be rendered from arbitrary viewpoints in real-time.
  arXiv  Detail & Related papers  (2024-10-17T13:19:32Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• Hierarchical Semantic Regularization of Latent Spaces in StyleGANs [53.98170188547775]
  We propose a Hierarchical Semantic Regularizer (HSR) which aligns the hierarchical representations learnt by the generator to corresponding powerful features learnt by pretrained networks on large amounts of data. HSR is shown to not only improve generator representations but also the linearity and smoothness of the latent style spaces, leading to the generation of more natural-looking style-edited images.
  arXiv  Detail & Related papers  (2022-08-07T16:23:33Z)
• NeurInt : Learning to Interpolate through Neural ODEs [18.104328632453676]
  We propose a novel generative model that learns a distribution of trajectories between two images. We demonstrate our approach's effectiveness in generating images improved quality as well as its ability to learn a diverse distribution over smooth trajectories for any pair of real source and target images.
  arXiv  Detail & Related papers  (2021-11-07T16:31:18Z)
• Toward Spatially Unbiased Generative Models [19.269719158344508]
  Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. We argue that the generators rely on their implicit positional encoding to render spatial content.
  arXiv  Detail & Related papers  (2021-08-03T04:13:03Z)
• Low-Rank Subspaces in GANs [101.48350547067628]
  This work introduces low-rank subspaces that enable more precise control of GAN generation. LowRankGAN is able to find the low-dimensional representation of attribute manifold. Experiments on state-of-the-art GAN models (including StyleGAN2 and BigGAN) trained on various datasets demonstrate the effectiveness of our LowRankGAN.
  arXiv  Detail & Related papers  (2021-06-08T16:16:32Z)
• Interpreting Spatially Infinite Generative Models [40.453301580034804]
  Recent work has shown that feeding spatial noise vectors into a fully convolutional neural network enables both generation of arbitrary resolution output images and training on arbitrary resolution training images. We provide a firm theoretical interpretation for infinite spatial generation, by drawing connections to spatial processes. Experiments on world map generation, panoramic images and texture synthesis verify the ability of $infty$-GAN to efficiently generate images of arbitrary size.
  arXiv  Detail & Related papers  (2020-07-24T09:00:41Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)
• Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization [4.529132742139768]
  Generative Adversarial Networks (GANs) try to learn the distribution of the real images in the manifold to generate samples that look real. We probe for ways to alleviate these problems for supervised GANs in this paper.
  arXiv  Detail & Related papers  (2020-01-22T16:27:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.