MOSAIC-GS：面向复杂动态环境的高级初始化单目场景重建
MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments
把深度、光流、动态分割与点跟踪等几何线索在初始化阶段融合，先估计初步三维动态再进入光度优化，这一「先几何初始化、后光度精修」的流程可直接迁移到单目动态 NeRF/3DGS 重建；用 Poly-Fourier 曲线对每个高斯轨迹做参数高效编码，也是动态场景紧凑表示的可复用手段。
原文依据 we leverage multiple geometric cues, such as depth, optical flow, dynamic object segmentation, and point tracking
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 MOSAIC-GS，一种基于高斯泼溅、从单目视频进行高保真动态场景重建的全新、完全显式且计算高效的方法。由于缺乏充分的多视图约束，单目重建本质上是病态的，这使得准确恢复物体几何与时序一致性尤为困难。为此，我们利用深度、光流、动态物体分割与点跟踪等多种几何线索。结合基于刚性的运动约束，这些线索使我们能够在初始化阶段估计初步的三维场景动态。在光度优化之前恢复场景动态，可减少对仅凭视觉外观进行运动推理的依赖，而这种推理在单目设定下往往存在歧义。为在支持非刚性形变的同时实现紧凑表示、快速训练与实时渲染，场景被分解为静态与动态两部分。动态部分中的每个高斯都被赋予一条以时间相关的 Poly-Fourier 曲线表示的轨迹，从而实现参数高效的运动编码。我们证明，MOSAIC-GS 相比现有方法实现了显著更快的优化与渲染，同时在标准单目动态场景基准上保持了与最优方法相当的重建质量。
英文原文摘要 1411 字符
We present MOSAIC-GS, a novel, fully explicit, and computationally efficient approach for high-fidelity dynamic scene reconstruction from monocular videos using Gaussian Splatting.Monocular reconstruction is inherently ill-posed due to the lack of sufficient multiview constraints, making accurate recovery of object geometry and temporal coherence particularly challenging. To address this, we leverage multiple geometric cues, such as depth, optical flow, dynamic object segmentation, and point tracking. Combined with rigidity-based motion constraints, these cues allow us to estimate preliminary 3D scene dynamics during an initialization stage.Recovering scene dynamics prior to the photometric optimization reduces reliance on motion inference from visual appearance alone, which is often ambiguous in monocular settings.To enable compact representations, fast training, and real-time rendering while supporting non-rigid deformations, the scene is decomposed into static and dynamic components. Each Gaussian in the dynamic part of the scene is assigned a trajectory represented as time-dependent Poly-Fourier curve for parameter-efficient motion encoding.We demonstrate that MOSAIC-GS achieves substantially faster optimization and rendering compared to existing methods,while maintaining reconstruction quality on par with state-of-the-art approaches across standard monocular dynamic scene benchmarks.