用3D人脸先验实现高清一致的人脸替换，保留表情与身份细节。
DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors
- 基于3D人脸先验设计四类解耦条件，精准控制表情与身份。
- 在FF++数据集上实现顶尖图像质量与身份保真度，表达更自然。
- 适配图像与视频，适合需要高保真人脸替换的场景。
人脸替换将源人脸的身份迁移到目标人脸，同时保留目标的面部表情、姿态、发型和背景等属性。现有先进方法虽取得良好效果，但常无意传递目标人脸的身份信息，影响表情细节与身份准确性。本文提出DynamicFace方法，结合扩散模型与即插即用的自适应注意力层，实现图像与视频中的人脸替换。首先引入四种基于3D人脸先验的细粒度面部条件，各条件相互解耦，实现精确独立控制。随后采用Face Former与ReferenceNet完成高层与细节级身份注入。在FF++数据集上的实验表明，该方法在人脸替换任务中达到当前最优表现，显著提升图像质量、身份保真度与表情准确性。框架可无缝适配图像与视频域。代码与结果将公开于项目主页：https://dynamic-face.github.io/
原文摘要 · Abstract (English)
Face swapping transfers the identity of a source face to a target face while retaining the attributes like expression, pose, hair, and background of the target face. Advanced face swapping methods have achieved attractive results. However, these methods often inadvertently transfer identity information from the target face, compromising expression-related details and accurate identity. We propose a novel method DynamicFace that leverages the power of diffusion models and plug-and-play adaptive attention layers for image and video face swapping. First, we introduce four fine-grained facial conditions using 3D facial priors. All conditions are designed to be disentangled from each other for precise and unique control. Then, we adopt Face Former and ReferenceNet for high-level and detailed identity injection. Through experiments on the FF++ dataset, we demonstrate that our method achieves state-of-the-art results in face swapping, showcasing superior image quality, identity preservation, and expression accuracy. Our framework seamlessly adapts to both image and video domains. Our code and results will be available on the project page: https://dynamic-face.github.io/
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。