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.
Matlab code implementing discrete multiscale optimization presented in:
Shai Bagon and Meirav Galun A Unified Multiscale Framework for Discrete Energy Minimization (arXiv'2012),
and Shai Bagon and Meirav Galun A Multiscale Framework for Challenging Discrete Optimization (NIPS Workshop on Optimization for Machine Learning 2012).
Matlab code implementing optimization algorithms presented in:
Shai Bagon and Meirav Galun Large Scale Correlation Clustering Optimization (arXiv'2011).
May be applicable to other graph partitioning problems as well.
Matlab wrapper to Veksler, Boykov, Zabih and Kolmogorov's implementation of Graph Cut algorithm. Use the following citation if you use this software. There is a simple example of image segmentation using GraphCuts.
Matlab wrapper to Lubor Ladicky, Pushmeet Kohli and Philip Torr's Minimizing Robust Higher Order Potentials using Move Making Algorithms. This software is for research purposes only. Use the following citations in any resulting publication.
Note: This wrapper provides an additional functionality of varying weights for the nodes participating in a higher order potential as described in the tech. report.
Approximate Nearest Neighbors
Matlab class providing interface to ANN library of David Mount and Sunil Arya.