ICCV 2019 Best Paper Award To Tomer Michaeli`s Group

Image generation learned from a single training Image

SinGAN–a new unconditional generative model trained on a single natural image is proposed. The model learns the image’s patch statistics across multiple scales, using a dedicated multi-scale adversarial training scheme; it can then be used to generate new realistic image samples that preserve the original patch distribution while creating new object configurations and structures.
Link To Paper Page