FAAC：基于锚定帧与条件控制的面部动画生成，实现高保真度与可编辑性
FAAC: Facial Animation Generation with Anchor Frame and Conditional Control for Superior Fidelity and Editability
AI总结：
本文提出FAAC方法，利用锚定帧和3D人脸模型条件控制，解决面部视频生成中的保真度、一致性和可编辑性问题，显著提升生成质量。
摘要：
近年来，扩散模型促进了视频生成的显著进步。然而，面部相关视频的创作仍面临面部保真度低、帧间一致性缺乏、可编辑性有限以及人体姿态不可控等问题。为解决这些挑战，我们提出了一种面部动画生成方法，该方法在确保帧间一致性的同时，增强了面部身份保真度和编辑能力。该方法引入了锚定帧的概念，以抵消在原始文本到图像模型中引入运动模块时生成能力的退化。我们针对此目标提出了两种策略：免训练和基于训练的锚定帧方法。我们方法的有效性已在多个代表性DreamBooth和LoRA模型上得到验证，在面部保真度、文本到图像的可编辑性和视频运动方面，相较于原始结果有显著提升。此外，我们引入了使用3D参数化人脸模型的条件控制，以捕捉准确的面部运动和表情。该解决方案通过集成多个控制信号，增强了面部动画生成的创作可能性。更多示例请访问https://paper-faac.github.io/。
英文摘要：
Over recent years, diffusion models have facilitated significant advancements in video generation. Yet, the creation of face-related videos still confronts issues such as low facial fidelity, lack of frame consistency, limited editability and uncontrollable human poses. To address these challenges, we introduce a facial animation generation method that enhances both face identity fidelity and editing capabilities while ensuring frame consistency. This approach incorporates the concept of an anchor frame to counteract the degradation of generative ability in original text-to-image models when incorporating a motion module. We propose two strategies towards this objective: training-free and training-based anchor frame methods. Our method's efficacy has been validated on multiple representative DreamBooth and LoRA models, delivering substantial improvements over the original outcomes in terms of facial fidelity, text-to-image editability, and video motion. Moreover, we introduce conditional control using a 3D parametric face model to capture accurate facial movements and expressions. This solution augments the creative possibilities for facial animation generation through the integration of multiple control signals. For additional samples, please visit https://paper-faac.github.io/.
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。
