揭示文本引导的3D人脸编辑方向
Revealing Directions for Text-guided 3D Face Editing
AI总结：
针对现有3D人脸编辑方法难平衡质量、效率与泛化性的问题，提出Face Clan方法，结合扩散模型与3D感知GAN，通过相反提示词扩散估计掩码再去噪揭示编辑方向，实现精准可控的文本引导3D人脸编辑，在多预训练GAN上验证了有效性。
摘要：
3D人脸编辑是多媒体领域的一项重要任务，旨在通过各类控制信号操控3D人脸模型。具备3D感知能力的GAN（生成对抗网络）的成功，提供了仅从2D单视图图像中学习得到的高表达性3D模型，推动研究人员在其潜在空间中挖掘语义编辑方向。然而，现有方法在质量、效率和泛化性的平衡上存在挑战。为解决该问题，我们探索了将扩散模型的优势引入3D感知GAN的可行性。本文提出Face Clan，这是一种快速且具备文本泛化性的方法，可基于任意属性描述生成和操控3D人脸。为实现解耦编辑，我们提出在一对相反提示词的约束下对潜在空间进行扩散，以估计出指示潜在码上感兴趣区域的掩码。随后基于该掩码，对被掩码的潜在码执行去噪，从而揭示编辑方向。我们的方法提供了精准可控的操控方式，支持用户通过文本描述直观自定义感兴趣区域。实验证明，Face Clan在多种预训练GAN上均具备有效性和泛化性，为文本引导的人脸编辑提供了直观且应用广泛的方案，为多媒体内容创作领域添砖加瓦。
英文摘要：
3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation.
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。
