We introduce a segmentation-guided approach to synthesise images that integrate features from two distinct domains. Images synthesised by our dual-domain model belong to one domain within the semantic mask, and to another in the rest of the image - smoothly integrated. We build on the successes of few-shot StyleGAN and single-shot semantic segmentation to minimise the amount of training required in utilising two domains. The method combines a few-shot cross-domain StyleGAN with a latent optimiser to achieve images containing features of two distinct domains. We use a segmentation-guided perceptual loss, which compares both pixel-level and activations between domain-specific and dual-domain synthetic images. Results demonstrate qualitatively and quantitatively that our model is capable of synthesising dual-domain images on a variety of objects (faces, horses, cats, cars), domains (natural, caricature, sketches) and part-based masks (eyes, nose, mouth, hair, car bonnet). The code is publicly available at: https://github.com/denabazazian/Dual-Domain-Synthesis.
翻译:我们对合成图像采用了分解制导法,将两个不同域的特征融合在一起。我们用双向方向模型合成的图像属于语义遮罩内的一个领域,而图像的其余部分则属于另一个领域 -- -- 顺利整合。我们以几发StyleGAN和单发语义分隔法的成功为基础,最大限度地减少了在使用两个领域方面所需的培训数量。这个方法将一个几发交叉式StyleGAN与一个隐性优化器结合起来,以取得包含两个不同域特征的图像。我们使用一种分解制制导感知性损失,将像素级和激活在特定领域和双向合成图像之间作比较。结果从质量和数量上表明,我们的模型能够将多种物体(面、马、猫、汽车)、领域(自然、漫画、草图)和部分面面面(眼、鼻子、嘴、头发、汽车、骨头)上的双向图像合成。代码在https://github.com/denabazaian/Dmalima-Domaisial上公开提供。