Recent advances in face manipulation using StyleGAN have produced impressive results. However, StyleGAN is inherently limited to cropped aligned faces at a fixed image resolution it is pre-trained on. In this paper, we propose a simple and effective solution to this limitation by using dilated convolutions to rescale the receptive fields of shallow layers in StyleGAN, without altering any model parameters. This allows fixed-size small features at shallow layers to be extended into larger ones that can accommodate variable resolutions, making them more robust in characterizing unaligned faces. To enable real face inversion and manipulation, we introduce a corresponding encoder that provides the first-layer feature of the extended StyleGAN in addition to the latent style code. We validate the effectiveness of our method using unaligned face inputs of various resolutions in a diverse set of face manipulation tasks, including facial attribute editing, super-resolution, sketch/mask-to-face translation, and face toonification.
翻译:使用 StyleGAN 进行面部操控的最新进展产生了令人印象深刻的结果。 然而, StyleGAN 的内在局限性仅限于以它事先培训过的固定图像分辨率刻出对齐面孔。 在本文中,我们提出一个简单而有效的限制解决方案,即使用放大变速法来重新缩放StyleGAN 浅层的可容纳场,而不会改变任何模型参数。 这使得浅层的固定大小小特征能够扩展为能够容纳可变分辨率的更大尺寸特征, 使其更牢固地描述不相容面孔的特征。 为了让真实面部面部转换和操作, 我们引入了一个相应的编码器, 提供扩展的StyleGAN 的第一层特征, 除了潜在样式代码之外。 我们验证了我们的方法的有效性, 使用各种面部操控任务中不同分辨率的不统一面部输入的面部。 包括面部感编辑、 超分辨率、 草图/ 图像对面翻译和脸感化。</s>