一种基于参考的3D语义感知框架，用于精确的局部面部属性编辑
A Reference-Based 3D Semantic-Aware Framework for Accurate Local Facial Attribute Editing
AI总结：
提出一种融合潜变量与参考图像优势的3D语义感知面部属性编辑框架，通过3D GAN反演和从粗到细的修复策略实现精确、3D一致且保持图像完整性的局部属性修改。
摘要：
面部属性编辑在合成具有特定特征且保持真实外观的人脸中起着至关重要的作用。尽管取得了进展，但在实现精确的、3D感知的属性修改方面仍存在挑战，这对于从不同角度一致且准确地表示人脸至关重要。当前方法在语义纠缠方面存在困难，并且缺乏在保持图像完整性的同时融合属性的有效指导。为了解决这些问题，我们引入了一种新颖的框架，融合了基于潜变量和基于参考的编辑方法的优势。我们的方法采用3D GAN反演技术，将参考图像中的属性嵌入到三平面空间中，确保3D一致性并实现多视角的真实感观察。我们利用混合技术和预测的语义掩码来定位精确的编辑区域，并将其与参考图像的上下文指导相结合。随后应用从粗到细的修复策略，以保留非目标区域的完整性，显著增强了真实感。我们的评估表明，在多种编辑任务中表现出卓越的性能，验证了我们框架在真实且适用的面部属性编辑中的有效性。
英文摘要：
Facial attribute editing plays a crucial role in synthesizing realistic faces with specific characteristics while maintaining realistic appearances. Despite advancements, challenges persist in achieving precise, 3D-aware attribute modifications, which are crucial for consistent and accurate representations of faces from different angles. Current methods struggle with semantic entanglement and lack effective guidance for incorporating attributes while maintaining image integrity. To address these issues, we introduce a novel framework that merges the strengths of latent-based and reference-based editing methods. Our approach employs a 3D GAN inversion technique to embed attributes from the reference image into a tri-plane space, ensuring 3D consistency and realistic viewing from multiple perspectives. We utilize blending techniques and predicted semantic masks to locate precise edit regions, merging them with the contextual guidance from the reference image. A coarse-to-fine inpainting strategy is then applied to preserve the integrity of untargeted areas, significantly enhancing realism. Our evaluations demonstrate superior performance across diverse editing tasks, validating our framework's effectiveness in realistic and applicable facial attribute editing.
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。
