基于身份约束人脸条件的高保真扩散人脸交换
High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
把身份条件与属性条件解耦注入、先保身份再微调属性对齐的两阶段条件控制思路，可直接迁移到任何人脸编辑/换脸扩散模型中，用于缓解多条件冲突；后训练阶段加入身份损失与对抗损失做精修的做法也可复用到其他身份保持生成任务。
原文依据 an identity-constrained attribute-tuning framework for face swapping that first ensures identity preservation and then fine-tunes for attribute alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人脸交换旨在将源人脸身份无缝迁移到目标人脸上，同时保留姿态、表情等目标属性。扩散模型凭借其优越的生成能力，近期在提升人脸交换质量方面展现出潜力。本文针对基于扩散模型的人脸交换中的两个关键挑战：身份保持优先于目标属性保持，以及身份条件与属性条件之间固有的冲突。为解决这些问题，我们提出一种面向人脸交换的身份约束属性调优框架，该框架首先确保身份保持，随后通过解耦的条件注入对属性对齐进行微调。我们进一步在后训练精修阶段引入身份损失与对抗损失以提升保真度。所提出的基于身份约束扩散模型的人脸交换方法在定性与定量评估中均优于现有方法，展现出更优的身份相似度与属性一致性，在高保真人脸交换上取得了新的最优性能。
英文原文摘要 1137 字符
Face swapping aims to seamlessly transfer a source facial identity onto a target while preserving target attributes such as pose and expression. Diffusion models, known for their superior generative capabilities, have recently shown promise in advancing face-swapping quality. This paper addresses two key challenges in diffusion-based face swapping: the prioritized preservation of identity over target attributes and the inherent conflict between identity and attribute conditioning. To tackle these issues, we introduce an identity-constrained attribute-tuning framework for face swapping that first ensures identity preservation and then fine-tunes for attribute alignment, achieved through a decoupled condition injection. We further enhance fidelity by incorporating identity and adversarial losses in a post-training refinement stage. Our proposed identity-constrained diffusion-based face-swapping model outperforms existing methods in both qualitative and quantitative evaluations, demonstrating superior identity similarity and attribute consistency, achieving a new state-of-the-art performance in high-fidelity face swapping.