MotionScale：以可扩展 4D 高斯泼溅重建动态场景的外观、几何与运动
MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting
以聚类中心基变换参数化的可扩展运动场，配合背景扩展与前景传播两阶段渐进优化，为单目视频长时序大场景的动态重建提供了可复用的运动表示与训练调度思路。
原文依据 a scalable motion field parameterized by cluster-centric basis transformations that adaptively expand to capture diverse and evolving motion patterns
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单目视频中真实感地重建动态 4D 场景，是理解物理世界的关键。尽管神经渲染近期取得了进展，现有方法在复杂环境中往往难以恢复准确的三维几何与时序一致的运 动。为应对这些挑战，我们提出 MotionScale，一个 4D 高斯泼溅框架，能够高效扩展到大规模场景与长序列，同时保持高保真的结构一致性与运动一致性。本方法的核心是由聚类中心基变换参数化的可扩展运动场，它能够自适应扩展，以捕捉多样且不断演化的运动模式。为确保长时长下的稳健重建，我们引入一种渐进式优化策略，包含两个解耦的传播阶段：1）背景扩展阶段，适应新出现的可见区域、细化相机位姿并显式建模瞬态阴影；2）前景传播阶段，通过专门的三阶段细化过程强制运动一致性。在具有挑战性的真实世界基准上的大量实验表明，MotionScale 在重建质量与时序稳定性上均显著优于最优方法。项目主页：https://hrzhou2.github.io/motion-scale-web/。
英文原文摘要 1336 字符
Realistic reconstruction of dynamic 4D scenes from monocular videos is essential for understanding the physical world. Despite recent progress in neural rendering, existing methods often struggle to recover accurate 3D geometry and temporally consistent motion in complex environments. To address these challenges, we propose MotionScale, a 4D Gaussian Splatting framework that scales efficiently to large scenes and extended sequences while maintaining high-fidelity structural and motion coherence. At the core of our approach is a scalable motion field parameterized by cluster-centric basis transformations that adaptively expand to capture diverse and evolving motion patterns. To ensure robust reconstruction over long durations, we introduce a progressive optimization strategy comprising two decoupled propagation stages: 1) A background extension stage that adapts to newly visible regions, refines camera poses, and explicitly models transient shadows; 2) A foreground propagation stage that enforces motion consistency through a specialized three-stage refinement process. Extensive experiments on challenging real-world benchmarks demonstrate that MotionScale significantly outperforms state-of-the-art methods in both reconstruction quality and temporal stability. Project page: https://hrzhou2.github.io/motion-scale-web/.