TY - GEN
T1 - SinGAN
T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
AU - Rott Shaham, Tamar
AU - Dekel, Tali
AU - Michaeli, Tomer
N1 - Publisher Copyright: © 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85081905989&partnerID=8YFLogxK
U2 - https://doi.org/10.1109/ICCV.2019.00467
DO - https://doi.org/10.1109/ICCV.2019.00467
M3 - منشور من مؤتمر
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 4569
EP - 4579
BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019
Y2 - 27 October 2019 through 2 November 2019
ER -