用视频中物体结构先验增强动态场景重建，提升细节与连贯性。
Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
- 利用视频分割和对极误差图生成精细物体掩码，指导深度优化
- 通过骨架采样与掩码重识别，实现稳定可靠的2D轨迹追踪
- 融合虚拟视角深度与支架投影损失，保留几何细节与运动一致性
我们提出一种完全自动化的单目RGB视频动态场景重建流水线。不设计新场景表示，而是增强驱动动态高斯点云的先验信息。视频分割结合对极误差图生成紧贴细长结构的物体级掩码，这些掩码（i）引导物体-深度损失以锐化一致的视频深度，（ii）支持基于骨架的采样与掩码引导的重识别，生成可靠且完整的二维轨迹。两个额外目标将优化后的先验嵌入重建阶段：虚拟视图深度损失消除伪影，支架投影损失将运动节点与轨迹绑定，保持精细几何与连贯运动。该系统超越以往单目动态场景重建方法，渲染效果显著更优。
原文摘要 · Abstract (English)
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
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。