3D neural style transfer has gained significant attention for its potential to provide user-friendly stylization with spatial consistency. However, existing 3D style transfer methods often fall short in terms of inference efficiency, generalization ability, and struggle to handle dynamic scenes with temporal consistency. In this paper, we introduce 4DStyleGaussian, a novel 4D style transfer framework designed to achieve real-time stylization of arbitrary style references while maintaining reasonable content affinity, multi-view consistency, and temporal coherence. Our approach leverages an embedded 4D Gaussian Splatting technique, which is trained using a reversible neural network for reducing content loss in the feature distillation process. Utilizing the 4D embedded Gaussians, we predict a 4D style transformation matrix that facilitates spatially and temporally consistent style transfer with Gaussian Splatting. Experiments demonstrate that our method can achieve high-quality and zero-shot stylization for 4D scenarios with enhanced efficiency and spatial-temporal consistency.
3D神经风格迁移因其能够提供用户友好的风格化并保持空间一致性而备受关注。然而，现有的3D风格迁移方法在推理效率、泛化能力方面往往不足，且在处理具有时间一致性的动态场景时存在挑战。在本文中，我们提出了一种新颖的4D风格迁移框架——4DStyleGaussian，旨在实现任意风格参考的实时风格化，同时保持合理的内容关联性、多视角一致性以及时间连贯性。我们的方法利用了嵌入式4D高斯散射技术，该技术通过可逆神经网络进行训练，从而在特征蒸馏过程中减少内容损失。借助嵌入的4D高斯，我们预测了一个4D风格变换矩阵，以实现具有高斯散射的空间和时间一致的风格迁移。实验表明，我们的方法在4D场景中能够实现高质量的零样本风格迁移，并在效率和时空一致性方面得到了显著提升。