ZDySS——使用 Gaussian Splatting 的零样本动态场景风格化
ZDySS -- Zero-Shot Dynamic Scene Stylization using Gaussian Splatting
AI总结：
针对动态场景示例风格化的时空一致性与风格泛化难题，提出基于 Gaussian Splatting 的零样本框架 ZDySS，通过在 Gaussian 特征向量上执行风格迁移提升跨帧一致性，并在真实场景中优于现有基线。
摘要：
基于示例图像对动态场景进行风格化，对于游戏制作、电影摄制以及增强现实和虚拟现实等多种现实应用至关重要。然而，在空间和时间两个维度上实现一致的风格化仍然是一项重大挑战。现有方法大多面向静态场景设计，并且通常需要针对每张风格图像执行优化过程，从而限制了其适应性。我们提出 ZDySS，这是一种用于动态场景的零样本风格化框架，使我们的模型能够在推理时泛化到此前未见过的风格图像。我们的方法采用 Gaussian splatting 进行场景表示，将每个 Gaussian 与一个学习到的特征向量相关联，该特征向量可为任意给定视角和时间戳渲染特征图。通过在学习到的特征向量而非渲染得到的特征图上应用风格迁移，我们增强了跨帧的时空一致性。在真实动态场景上的测试中，我们的方法相较最先进的基线表现出更优的性能和连贯性，使其成为适用于实际应用的稳健解决方案。
英文摘要：
Stylizing a dynamic scene based on an exemplar image is critical for various real-world applications, including gaming, filmmaking, and augmented and virtual reality. However, achieving consistent stylization across both spatial and temporal dimensions remains a significant challenge. Most existing methods are designed for static scenes and often require an optimization process for each style image, limiting their adaptability. We introduce ZDySS, a zero-shot stylization framework for dynamic scenes, allowing our model to generalize to previously unseen style images at inference. Our approach employs Gaussian splatting for scene representation, linking each Gaussian to a learned feature vector that renders a feature map for any given view and timestamp. By applying style transfer on the learned feature vectors instead of the rendered feature map, we enhance spatio-temporal consistency across frames. Our method demonstrates superior performance and coherence over state-of-the-art baselines in tests on real-world dynamic scenes, making it a robust solution for practical applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
