SinGAN swMATH ID: 43428 Software Authors: Tamar Rott Shaham, Tali Dekel, Tomer Michaeli Description: SinGAN: Learning a Generative Model from a Single Natural Image. We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within the image, and is then able to generate high quality, diverse samples that carry the same visual content as the image. SinGAN contains a pyramid of fully convolutional GANs, each responsible for learning the patch distribution at a different scale of the image. This allows generating new samples of arbitrary size and aspect ratio, that have significant variability, yet maintain both the global structure and the fine textures of the training image. In contrast to previous single image GAN schemes, our approach is not limited to texture images, and is not conditional (i.e. it generates samples from noise). User studies confirm that the generated samples are commonly confused to be real images. We illustrate the utility of SinGAN in a wide range of image manipulation tasks. Homepage: https://arxiv.org/abs/1905.01164 Source Code: https://github.com/tamarott/SinGAN Dependencies: Python Keywords: SinGAN; Single Natural Image; Computer Vision; Pattern Recognition; arXiv_cs.CV; unconditional generative model; Python; GANs Related Software: ImageNet; StarGAN; Adam; Python; SynSin; PyTorch; MS-COCO; SketchyGAN; TensorFlow; Mimicry; Wasserstein GAN; GANSim; FLUVSIM; ALLUVSIM; PointNet; MNIST; CamNet; MVSNet; Fashion-MNIST; Make3D Cited in: 4 Publications Standard Articles 1 Publication describing the Software Year SinGAN: Learning a Generative Model from a Single Natural Image Tamar Rott Shaham, Tali Dekel, Tomer Michaeli 2019 all top 5 Cited by 12 Authors 1 Azencot, Omri 1 Cohen, Ido 1 Gilboa, Guy 1 Hou, Jie 1 Hou, Lijun 1 Ji, Xin 1 Lifshits, Pavel 1 Ni, Jiancheng 1 Szeliski, Richard 1 Zhang, Anqin 1 Zhang, Susu 1 Zhou, Zili Cited in 4 Serials 1 Computational Geosciences 1 SIAM Journal on Imaging Sciences 1 Texts in Computer Science 1 Mathematical Foundations of Computing all top 5 Cited in 6 Fields 3 Computer science (68-XX) 2 Information and communication theory, circuits (94-XX) 1 Partial differential equations (35-XX) 1 Calculus of variations and optimal control; optimization (49-XX) 1 Numerical analysis (65-XX) 1 Geophysics (86-XX) Citations by Year