Generative 3D face models featuring disentangled controlling factors hold immense potential for diverse applications in computer vision and computer graphics. However, previous 3D face modeling methods face a challenge as they demand specific labels to effectively disentangle these factors. This becomes particularly problematic when integrating multiple 3D face datasets to improve the generalization of the model. Addressing this issue, this paper introduces a Weakly-Supervised Disentanglement Framework, denoted as WSDF, to facilitate the training of controllable 3D face models without an overly stringent labeling requirement. Adhering to the paradigm of Variational Autoencoders (VAEs), the proposed model achieves disentanglement of identity and expression controlling factors through a two-branch encoder equipped with dedicated identity-consistency prior. It then faithfully re-entangles these factors via a tensor-based combination mechanism. Notably, the introduction of the Neutral Bank allows precise acquisition of subject-specific information using only identity labels, thereby averting degeneration due to insufficient supervision. Additionally, the framework incorporates a label-free second-order loss function for the expression factor to regulate deformation space and eliminate extraneous information, resulting in enhanced disentanglement. Extensive experiments have been conducted to substantiate the superior performance of WSDF. Our code is available at https://github.com/liguohao96/WSDF.

翻译：生成式三维人脸模型具备解耦的控制因子，在计算机视觉和计算机图形学领域具有广阔应用前景。然而，现有三维人脸建模方法面临挑战：它们需要特定标签才能有效解耦这些因子，这在整合多个三维人脸数据集以提升模型泛化能力时尤为棘手。针对该问题，本文提出弱监督解耦框架（WSDF），旨在无需严苛标注条件下训练可控三维人脸模型。该模型遵循变分自编码器（VAEs）范式，通过配备专用身份一致性先验的双分支编码器实现身份与表情控制因子的解耦，并借助基于张量的组合机制实现因子忠实重组。值得注意的是，中性库（Neutral Bank）的引入使得仅需身份标签即可精确获取受试者特定信息，从而避免因监督不足导致的性能退化。此外，框架针对表情因子设计了无标签二阶损失函数以约束形变空间并消除冗余信息，从而实现更优解耦效果。大量实验验证了WSDF的卓越性能。相关代码已开源：https://github.com/liguohao96/WSDF。