通过语义保持与伪成对监督提升人脸风格化质量
Advancing Facial Stylization through Semantic Preservation Constraint and Pseudo-Paired Supervision
- 引入语义保持约束和伪成对监督，增强风格迁移内容一致性
- 在CelebA-HQ数据集上生成结果更接近原图，视觉质量显著提升
- 无需复杂结构设计，支持多模态和参考引导风格化
人脸风格化旨在将面部图像转化为美观、高质量的风格化肖像，其核心挑战在于准确学习目标风格的同时保持与原始图像的内容一致性。尽管基于StyleGAN的方法已取得显著进展，生成结果仍存在伪影或与源图相似度不足的问题。我们认为这些问题源于生成器在风格化过程中忽略语义偏移。为此，我们提出一种结合语义保持约束与伪成对监督的人脸风格化方法，以增强内容对应关系并改善风格化效果。此外，我们开发了构建多层级伪成对数据集的方法以实现监督约束。在此框架基础上，我们实现了无需复杂网络设计或额外训练的灵活多模态及参考引导风格化。实验表明，该方法在保持高保真度的同时生成更具美感的人脸风格化图像，优于以往方法。
原文摘要 · Abstract (English)
Facial stylization aims to transform facial images into appealing, high-quality stylized portraits, with the critical challenge of accurately learning the target style while maintaining content consistency with the original image. Although previous StyleGAN-based methods have made significant advancements, the generated results still suffer from artifacts or insufficient fidelity to the source image. We argue that these issues stem from neglecting semantic shift of the generator during stylization. Therefore, we propose a facial stylization method that integrates semantic preservation constraint and pseudo-paired supervision to enhance the content correspondence and improve the stylization effect. Additionally, we develop a methodology for creating multi-level pseudo-paired datasets to implement supervisory constraint. Furthermore, building upon our facial stylization framework, we achieve more flexible multimodal and reference-guided stylization without complex network architecture designs or additional training. Experimental results demonstrate that our approach produces high-fidelity, aesthetically pleasing facial style transfer that surpasses previous methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。