4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting
This addresses the need for efficient and consistent style transfer in dynamic 3D scenes, though it appears incremental as it builds on existing Gaussian Splatting techniques.
The paper tackles the problem of inefficient and inconsistent 3D style transfer for dynamic scenes by introducing 4DStyleGaussian, a framework that achieves real-time, zero-shot 4D style transfer with high-quality results and enhanced spatial-temporal consistency.
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.