Скачать или смотреть Vadim Sushko: One-Shot Synthesis of Images and Segmentation Masks

Existing GAN approaches for joint synthesis of images and segmentation masks are typically trained using large amounts of image data, which limits their utilization in restricted image domains. In this work, we take a step to reduce this limitation, introducing the task of one-shot image-mask synthesis: generate diverse images and their segmentation masks given only a single labelled example. Inspired by recent architectural developments of single-image GANs, we introduce our OSMIS model, which enables the synthesis of segmentation masks that are precisely aligned to generated images in the one-shot regime. Besides achieving a high fidelity of annotations, OSMIS outperforms existing single-image GAN models in image synthesis quality and diversity.