Existing face stylization methods always acquire the presence of the target (style) domain during the translation process, which violates privacy regulations and limits their applicability in real-world systems. To address this issue, we propose a new method called MODel-drIven Face stYlization (MODIFY), which relies on the generative model to bypass the dependence of the target images. Briefly, MODIFY first trains a generative model in the target domain and then translates a source input to the target domain via the provided style model. To preserve the multimodal style information, MODIFY further introduces an additional remapping network, mapping a known continuous distribution into the encoder's embedding space. During translation in the source domain, MODIFY fine-tunes the encoder module within the target style-persevering model to capture the content of the source input as precisely as possible. Our method is extremely simple and satisfies versatile training modes for face stylization. Experimental results on several different datasets validate the effectiveness of MODIFY for unsupervised face stylization.

翻译：现有的人脸风格化方法在迁移过程中始终需要目标（风格）域的存在，这既违反隐私法规又限制了其在真实系统中的应用。为解决该问题，我们提出名为MODel-drIven Face stYlization（MODIFY）的新方法，该方法通过生成模型绕过对目标图像的依赖。具体而言，MODIFY首先在目标域训练生成模型，随后通过提供的风格模型将源输入迁移至目标域。为保留多模态风格信息，MODIFY进一步引入附加重映射网络，将已知连续分布映射至编码器的嵌入空间。在源域迁移过程中，MODIFY微调目标风格保持模型中的编码器模块，以尽可能精确地捕获源输入的内容。该方法极为简洁，可支持多种训练模式的人脸风格化任务。多个不同数据集上的实验结果验证了MODIFY在无监督人脸风格化中的有效性。