Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
arXiv:1712.01551
Abstract
Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fill the gap, this paper first formulates the problem of generating manifold-valued images and exploits three typical instances: hue-saturation-value (HSV) color image generation, chromaticity-brightness (CB) color image generation, and diffusion-tensor (DT) image generation. For the proposed generative modeling problem, we then introduce a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds, enabling us to achieve a tractable objective under the WGAN framework. In addition, we recommend three benchmark datasets that are CIFAR-10 HSV/CB color images, ImageNet HSV/CB color images, UCL DT image datasets. On the three datasets, we experimentally demonstrate the proposed manifold-aware WGAN model can generate more plausible manifold-valued images than its competitors.
arXiv commentAccepted by AAAI 2019
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
- Spectral Normalization for Generative Adversarial Networks
- Pixel Recurrent Neural Networks
- Energy-based Generative Adversarial Network
- A Riemannian Network for SPD Matrix Learning
- A Second Order Non-Smooth Variational Model for Restoring Manifold-Valued Images
- Are GANs Created Equal? A Large-Scale Study
- Second Order Differences of Cyclic Data and Applications in Variational Denoising
- A Geometric View of Optimal Transportation and Generative Model
- Inpainting of Cyclic Data using First and Second Order Differences