RiGS: 从单目视频中的刚性感知4D高斯泼溅
RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video
AI总结：
提出RiGS，通过静态、刚性和瞬态三种高斯原语分别建模不同时间尺度的运动，并利用目标动态掩码和场景流引导实现单目视频动态场景重建，在新视角合成任务上达到最优性能。
摘要：
从单目视频重建动态3D场景是一项基本但极具挑战性的任务，因为现实世界的运动通常涉及长期平滑变换和短期复杂变形。现有方法要么难以保持时间一致性，要么由于运动建模能力有限而无法捕捉高频动态。在这项工作中，我们提出了刚性感知4D高斯泼溅（RiGS），它同时捕捉多个时间尺度上的运动。具体来说，RiGS引入了三种类型的高斯原语：静态、刚性和瞬态，分别表示静态背景、长期低频运动和短期高频动态。提出了一种对象级动态掩码来聚合长距离时空运动信息，并指导静态和动态区域的分解。为了联合建模跨尺度的运动，允许刚性高斯根据其时间持续期转变为瞬态高斯，并且两者都在场景流引导下进行优化，提供密集的3D运动监督。大量实验表明，RiGS在新视角合成基准测试中达到了最先进的性能。代码可在\url{https://github.com/ladvu/RiGS}获取。
英文摘要：
Reconstructing dynamic 3D scenes from monocular videos is a fundamental yet highly challenging task, as real-world motions often involve both long-term smooth transformations and short-term complex deformations. Existing methods either struggle to maintain temporal consistency or fail to capture high-frequency dynamics due to limited motion modeling capacity. In this work, we present Rigid-aware 4D Gaussian Splatting (RiGS), which simultaneously captures motions across multiple temporal scales. Specifically, RiGS introduces three types of Gaussian primitives: static, rigid, and transient, which represent static backgrounds, long-term low-frequency motions, and short-term high-frequency dynamics, respectively. An object-wise dynamic mask is proposed to aggregate long-range spatiotemporal motion information and guide the decomposition of static and dynamic regions. To jointly model motion across scales, rigid Gaussians are allowed to transition into transient Gaussians based on their temporal duration, and both are optimized under scene flow guidance, providing dense 3D motion supervision. Extensive experiments demonstrate that RiGS achieves state-of-the-art performance on novel view synthesis benchmarks. Code is available at \hyperlink{https://github.com/ladvu/RiGS}{https://github.com/ladvu/RiGS}.
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。
