Abstract
We introduce a fully automatic pipeline for dynamic scene reconstruction from casually captured monocular RGB videos. Rather than designing a new scene representation, we enhance the priors that drive Dynamic Gaussian Splatting. Video segmentation combined with epipolar-error maps yields object-level masks that closely follow thin structures; these masks (i) guide an object-depth loss that sharpens the consistent video depth, and (ii) support skeleton-based sampling plus mask-guided re-identification to produce reliable, comprehensive 2-D tracks. Two additional objectives embed the refined priors in the reconstruction stage: a virtual-view depth loss removes floaters, and a scaffold-projection loss ties motion nodes to the tracks, preserving fine geometry and coherent motion. The resulting system surpasses previous monocular dynamic scene reconstruction methods and delivers visibly superior renderings
Abstract (translated)
我们介绍了一种从随意拍摄的单目RGB视频中进行动态场景重建的全自动管道。而不是设计一个新的场景表示，我们改进了驱动动态高斯点置（Dynamic Gaussian Splatting）的先验知识。结合视频分割和极线误差图可以产生与细长结构紧密贴合的对象级蒙版；这些蒙版(i)引导一个对象深度损失，以锐化一致的视频深度，并(ii)支持基于骨架采样以及蒙版引导下的重新识别，从而生成可靠且全面的二维轨迹。两个额外的目标将精炼后的先验知识嵌入到重建阶段：虚拟视图深度损失可以去除漂浮物，而支架投影损失则将运动节点绑定至轨迹中，保留了精细几何结构和连贯的运动。该系统超越了之前的单目动态场景重建方法，并提供了明显更优的渲染效果。
URL
https://arxiv.org/abs/2512.11356
