DiffSwap++：用于身份保留人脸交换的3D潜在控制扩散模型
DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping
AI总结：
本研究提出DiffSwap++，一种融入3D人脸潜在特征的扩散人脸交换方法，可在保留源身份的同时维持目标姿态表情，在多数据集实验及评估中性能优于现有方法。
摘要：
基于扩散的方法近期在人脸交换任务中取得了优异成果，相比传统基于GAN的方法视觉质量更优。但即便是最先进的模型，在挑战性姿态和表情场景下仍存在细粒度伪影和身份保留不佳的问题。现有方法的关键局限在于未能有效利用3D人脸结构，而3D结构对解耦身份与姿态、表情至关重要。本研究提出DiffSwap++，一种在训练过程中融入3D人脸潜在特征的新型基于扩散的人脸交换流水线。通过用3D感知表征引导生成过程，该方法增强了几何一致性并提升了人脸身份与外观属性的解耦能力。我们进一步设计了一种扩散架构，使其去噪过程同时以身份嵌入和人脸关键点为条件，从而实现高保真且身份保留的人脸交换。在CelebA、FFHQ和CelebV-Text数据集上的大量实验表明，DiffSwap++在保留源身份的同时，能更好地维持目标姿态和表情，性能优于现有方法。此外，我们引入了生物特征风格评估并开展用户研究，以进一步验证该方法的真实性和有效性。代码将在该httpsURL上公开提供。
英文摘要：
Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-art models often suffer from fine-grained artifacts and poor identity preservation, particularly under challenging poses and expressions. A key limitation of existing approaches is their failure to meaningfully leverage 3D facial structure, which is crucial for disentangling identity from pose and expression. In this work, we propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training. By guiding the generation process with 3D-aware representations, our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes. We further design a diffusion architecture that conditions the denoising process on both identity embeddings and facial landmarks, enabling high-fidelity and identity-preserving face swaps. Extensive experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression. Additionally, we introduce a biometric-style evaluation and conduct a user study to further validate the realism and effectiveness of our approach. Code will be made publicly available at https://github.com/WestonBond/DiffSwapPP
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。
