论文标题
使用分割引导的GAN的双域图像合成
Dual-Domain Image Synthesis using Segmentation-Guided GAN
论文作者
论文摘要
我们引入了一种分割引导的方法，以合成从两个不同域的特征整合特征的图像。由我们的双重域模型合成的图像属于语义掩码中的一个域，而在图像的其余部分中属于另一个域 - 平稳集成。我们基于少量型样式和单次语义细分的成功，以最大程度地减少利用两个域所需的培训量。该方法结合了一些射击的跨域风格和潜在优化器，以实现包含两个不同域特征的图像。我们使用分割引导的感知损失，该损失比较了像素级和域特异性和双域合成图像之间的激活。结果表明，定性和定量地证明了我们的模型能够在各种物体（面，马，猫，汽车），域（自然，讽刺，漫画，草图）和零件面具（眼睛，鼻子，鼻子，嘴，嘴，头发，头发，汽车上）上合成双域图像。该代码可在以下网址公开获取：https：//github.com/denabazazian/dual-domain-synthesis。
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.
