用三类高斯点捕捉多尺度动态，让单目视频生成更连贯的4D场景。
RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video
- 分三类高斯点：静态、刚性、瞬态，分别对应背景、慢动、快动。
- 刚性点可转为瞬态点，结合场景流优化，实现跨时序运动建模。
- 适合需要高精度动态重建的视觉重建与虚拟现实应用。
从单目视频重建动态3D场景是基础但极具挑战的任务，因真实运动常包含长期平滑变化和短期复杂形变。现有方法或难以保持时间一致性，或受限于运动建模能力而忽略高频动态。本文提出刚性感知4D高斯点渲染（RiGS），同时捕捉多时序尺度的运动。RiGS引入三类高斯原语：静态、刚性、瞬态，分别表示静态背景、长期低频运动和短期高频动态。提出物体级动态掩码，聚合长程时空运动信息，指导静态与动态区域分解。为联合建模多尺度运动，刚性高斯点可根据时长转化为瞬态点，二者均在场景流引导下优化，提供稠密3D运动监督。大量实验表明，RiGS在新视角合成基准上达到当前最优性能。代码已开源：https://github.com/ladvu/RiGS。
原文摘要 · Abstract (English)
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}.
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。