SinGAN: Learning a Generative Model From a Single Natural Image
Autor: | Tali Dekel, Tomer Michaeli, Tamar Rott Shaham |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering Pattern recognition 02 engineering and technology Iterative reconstruction Real image Image (mathematics) Range (mathematics) Generative model Pyramid 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Noise (video) Artificial intelligence Pyramid (image processing) business Image resolution |
Zdroj: | ICCV |
DOI: | 10.1109/iccv.2019.00467 |
Popis: | 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. ICCV 2019 |
Databáze: | OpenAIRE |
Externí odkaz: |