StyleGANEX：基于StyleGAN的非裁剪对齐人脸操控方法
StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
AI总结：
针对StyleGAN仅能处理固定分辨率裁剪对齐人脸的局限，提出基于空洞卷积扩展浅层感受野的StyleGANEX及配套编码器，可在不改模型参数的情况下实现多分辨率未对齐人脸的多种操控任务。
摘要：
近年来基于StyleGAN的人脸操控研究已取得亮眼成果，但StyleGAN本质上受限于其预训练时的固定图像分辨率，仅能处理裁剪对齐的人脸。本文提出一种简单有效的解决方案：通过空洞卷积调整StyleGAN浅层的感受野，且不修改任何模型参数。该方法可将浅层的固定尺寸小特征扩展为能适配可变分辨率的更大特征，使其在表征未对齐人脸时更具鲁棒性。为实现真实人脸的反转与操控，我们提出了对应的编码器，除了提供隐层风格码外，还能输出扩展后StyleGAN的第一层特征。我们在多种人脸操控任务（包括人脸属性编辑、超分辨率、草图/掩码转人脸、人脸卡通化）中，使用不同分辨率的未对齐人脸输入验证了方法的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
