This paper presents the first significant work on directly predicting 3D face landmarks on neural radiance fields (NeRFs). Our 3D coarse-to-fine Face Landmarks NeRF (FLNeRF) model efficiently samples from a given face NeRF with individual facial features for accurate landmarks detection. Expression augmentation is applied to facial features in a fine scale to simulate large emotions range including exaggerated facial expressions (e.g., cheek blowing, wide opening mouth, eye blinking) for training FLNeRF. Qualitative and quantitative comparison with related state-of-the-art 3D facial landmark estimation methods demonstrate the efficacy of FLNeRF, which contributes to downstream tasks such as high-quality face editing and swapping with direct control using our NeRF landmarks. Code and data will be available. Github link: https://github.com/ZHANG1023/FLNeRF.

翻译：本文首次在神经辐射场（NeRF）上实现了三维人脸特征点的直接预测。我们提出的三维粗到细人脸特征点NeRF模型（FLNeRF）能够从给定的人脸NeRF中高效采样具有个体面部特征的样本，以实现精确的特征点检测。在精细尺度上对面部特征进行表情增强，以模拟大范围的情绪变化，包括夸张的面部表情（如鼓腮、张大嘴巴、眨眼），用于训练FLNeRF。与当前最先进的三维人脸特征点估计方法进行的定性与定量对比表明，FLNeRF的有效性使其能够通过直接控制NeRF特征点，为高质量人脸编辑与交换等下游任务提供支持。代码与数据将公开提供。GitHub链接：https://github.com/ZHANG1023/FLNeRF。