InGAN: Capturing and Remapping the "DNA" of a Natural Image
arXiv:1812.00231
Abstract
Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured by its unique distribution of patches. In this paper we propose an "Internal GAN" (InGAN) - an image-specific GAN - which trains on a single input image and learns its internal distribution of patches. It is then able to synthesize a plethora of new natural images of significantly different sizes, shapes and aspect-ratios - all with the same internal patch-distribution (same "DNA") as the input image. In particular, despite large changes in global size/shape of the image, all elements inside the image maintain their local size/shape. InGAN is fully unsupervised, requiring no additional data other than the input image itself. Once trained on the input image, it can remap the input to any size or shape in a single feedforward pass, while preserving the same internal patch distribution. InGAN provides a unified framework for a variety of tasks, bridging the gap between textures and natural images.
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Spectral Normalization for Generative Adversarial Networks
- A guide to convolution arithmetic for deep learning
- Texture Synthesis Using Convolutional Neural Networks
- Non-Stationary Texture Synthesis by Adversarial Expansion
- Texture Synthesis with Spatial Generative Adversarial Networks
Cited by in corpus (6)
- Contrastive Learning for Unpaired Image-to-Image Translation
- Self-Supervised Policy Adaptation during Deployment
- Learning Detail-Structure Alternative Optimization for Blind Super-Resolution
- Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
- Video Deblurring by Fitting to Test Data
- Learning to See by Looking at Noise