先验增强的高斯点云法用于从随意视频中动态场景重建
Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
AI总结：
本文提出一种基于先验增强的动态场景重建方法，通过改进高斯点云法和引入虚拟视图深度损失，提升单目视频重建的精度和渲染质量。
摘要：
我们介绍了一个完全自动的管道，用于从随意拍摄的单目RGB视频中进行动态场景重建。与其设计新的场景表示，我们增强了驱动动态高斯点云法的先验。视频分割结合极角误差图产生对象级别的掩码，这些掩码紧密跟随细长结构；这些掩码（i）指导一个对象深度损失，使一致的视频深度更清晰，（ii）支持基于骨架的采样加上掩码引导的重新识别，以产生可靠且全面的2D轨迹。两个额外的目标将细化的先验嵌入重建阶段：虚拟视图深度损失去除漂浮物，骨架投影损失将运动节点与轨迹联系起来，保持精细几何和一致的运动。所得到的系统超越了以往的单目动态场景重建方法，并提供了明显更优的渲染效果。
英文摘要：
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
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。
