无需标注即可分割3D人脸并精准编辑，支持跨人物部件替换。
FaceParts: Segmentation and Editing of Gaussian Splatting
- 直接在高斯点云上分解人脸部件，结合特征解耦与密度聚类。
- 跨人物替换后保持身份一致（ID=0.943），表情/姿态差异极小。
- 适合虚拟人、游戏角色的快速个性化定制，无需手工建模。
面部编辑在娱乐、虚拟现实和数字形象中有重要应用。现有方法多基于2D图像生成模型，而3D场景通常依赖繁琐的手动操作。本文提出FaceParts框架，实现高斯点云人脸的无监督分割与编辑。不同于传统2D或网格辅助方法，本方法直接在高斯域工作，无需标注即可将人脸分解为语义一致的面部部件。通过特征解耦、基于密度的聚类及FLAME锚定部件迁移，实现精确编辑与跨人物部件交换。在包含11名被试的NeRSemble数据集上实验表明，可鲁棒分离胡须、眉毛、眼睛、胡子等特征。定量评估显示，转移后的部件能适应不同姿态与表情，同时保持身份一致性（ID=0.943），平均表情距离（AED=0.021）与平均姿态距离（APD=0.004）均很低。
原文摘要 · Abstract (English)
Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentanglement, density-based clustering, and FLAME-anchored part transfer, enabling precise editing and cross-avatar part swapping. Experiments on the NeRSemble dataset with 11 subjects demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).
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。