ExSinGAN: Learning an Explainable Generative Model from a Single Image
This work addresses the challenge of single-image generation for computer vision applications, presenting an incremental improvement over prior methods by incorporating both internal and external information.
The paper tackles the problem of generating images from a single sample by proposing ExSinGAN, a hierarchical framework that learns an explainable generative model through cascaded GANs for structure, semantics, and texture, achieving competitive generalization ability for image manipulation tasks.
Generating images from a single sample, as a newly developing branch of image synthesis, has attracted extensive attention. In this paper, we formulate this problem as sampling from the conditional distribution of a single image, and propose a hierarchical framework that simplifies the learning of the intricate conditional distributions through the successive learning of the distributions about structure, semantics and texture, making the process of learning and generation comprehensible. On this basis, we design ExSinGAN composed of three cascaded GANs for learning an explainable generative model from a given image, where the cascaded GANs model the distributions about structure, semantics and texture successively. ExSinGAN is learned not only from the internal patches of the given image as the previous works did, but also from the external prior obtained by the GAN inversion technique. Benefiting from the appropriate combination of internal and external information, ExSinGAN has a more powerful capability of generation and competitive generalization ability for the image manipulation tasks compared with prior works.