用高斯点云实现零样本4D风格迁移，实时且保持时空一致性。
4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting
- 基于可逆神经网络训练4D高斯点云，降低特征蒸馏中的内容损失。
- 支持任意风格参考的零样本4D风格迁移，生成结果具空间与时间一致性。
- 适用于动态场景实时风格化，效率高于传统方法，适合影视动画生成。
3D神经风格迁移因其能提供具有空间一致性的用户友好风格化而受到广泛关注。然而，现有方法在推理效率、泛化能力方面表现不足，且难以处理具有时序一致性的动态场景。本文提出4DStyleGaussian，一种新型4D风格迁移框架，可在保持合理内容保真度、多视角一致性与时序连贯性的前提下，实现任意风格参考的实时风格化。该方法采用嵌入式4D高斯点云技术，通过可逆神经网络训练以减少特征蒸馏过程中的内容损失。利用4D嵌入高斯点云，预测4D风格变换矩阵，实现基于高斯点云的空间-时间一致风格迁移。实验表明，该方法在4D场景中实现了高质量、零样本风格迁移，同时提升了效率与时空一致性。
原文摘要 · Abstract (English)
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.
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。