发表机构
University of Science and Technology of Hanoi（河内科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对少样本面部表情合成问题，提出ICEF框架，将静态身份辐射分量与动态表情变形分量解缠，引入身份保留正则化器，纳入置信度加权条件特征扭曲步骤，提升新表情渲染质量与身份一致性。
AI 中文摘要
神经辐射场（NeRF）已实现3D场景的逼真新视角合成，在面部领域也被扩展用于从少量图像重建和动画化3D面部模型。然而，现有的少样本动态NeRF面部表情编辑方法通常基于目标表情参数扭曲单个学习到的特征体，这可能导致身份特定的外观细节（皮肤纹理、精细几何结构）在模型被驱动到远离少样本输入集中所见表情时发生漂移。我们提出身份一致的表情场（ICEF）框架，它明确地将静态的、身份特定的辐射分量与动态的、表情条件变形分量解缠，并引入身份保留正则化器，约束变形网络仅修改与表情相关区域，同时保持身份特定的规范外观不变。ICEF还纳入了置信度加权条件特征扭曲步骤，降低在参数空间中远离观察到的少样本输入的目标表情的不可靠扭曲权重，减轻了先前少样本动态NeRF方法在推断新表情时出现的伪影。我们将ICEF与先前的少样本动态NeRF、静态3D感知面部生成和解缠面部编辑辐射场方法相关联，并描述了一种评估协议，用于测量新表情渲染质量，特别是在一系列表情参数外推距离上的身份一致性指标。
英文摘要
Neural Radiance Fields (NeRF) have enabled photorealistic novel-view synthesis of 3D scenes and, in the facial domain, have been extended to reconstruct and animate 3D face models from a small number of images. However, existing few-shot dynamic NeRF methods for facial expression editing typically warp a single learned feature volume conditioned on target expression parameters, which can cause identity-specific appearance details (skin texture, fine geometric structure) to drift when the model is driven toward expressions far from those seen in the few-shot input set. We propose Identity-Consistent Expression Fields (ICEF), a framework that explicitly disentangles a static, identity-specific radiance component from a dynamic, expression-conditioned deformation component, and introduces an identity preservation regularizer that constrains the deformation network to modify only expression-relevant regions while leaving identity-specific canonical appearance untouched. ICEF further incorporates a confidence-weighted conditional feature warping step that down-weights unreliable warps for target expressions that are far, in parameter space, from the observed few-shot inputs, mitigating artifacts observed in prior few-shot dynamic NeRF methods when extrapolating to novel expressions. We relate ICEF to prior few-shot dynamic NeRF, static 3D-aware face generation, and disentangled face-editing radiance field methods, and describe an evaluation protocol measuring both novel-expression rendering quality and, specifically, identity-consistency metrics across a range of expression-parameter extrapolation distances.
