SV-GS：基于骨架驱动高斯泼溅的稀疏视角四维重建
SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting
把骨架关节位姿估计与细粒度形变解耦，只让关节位姿随时间变化，从而在稀疏时序观测下实现平滑运动插值并保留几何细节；该思路可直接迁移到稀疏相机下的动态高斯泼溅重建与单目视频新视角合成。
原文依据 By making only the joint pose estimator time-dependent, our model enables smooth motion interpolation while preserving learned geometric details.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论重建在大范围区域内运动的动态目标具有挑战性。标准的动态物体重建方法要求视角空间与时序维度上均有稠密覆盖，通常依赖在每个时间步采集的多视角视频。然而，此类设置只在受限环境中才可实现。在真实场景中，观测往往在时间上稀疏，且来自不同视角的采集也很稀疏（例如来自监控摄像头），这使得动态重建高度病态。我们提出 SV-GS，一个在稀疏观测下同时估计形变模型与物体随时间运动的框架。为初始化 SV-GS，我们利用一个粗略的骨架图与一个初始静态重建作为输入来引导运动估计。（后文我们将表明这一输入要求可以被放宽。）本方法优化一个由粗粒度骨架关节位姿估计器与细粒度形变模块组成的骨架驱动形变场。通过仅使关节位姿估计器依赖于时间，我们的模型能够在保留已学习几何细节的同时实现平滑的运动插值。在合成数据集上的实验表明，在稀疏观测下本方法在 PSNR 上以最高 34% 的优势优于现有方法，并且在真实数据集上尽管使用的帧数显著更少，仍达到与稠密单目视频方法相当的性能。此外，我们证明输入的初始静态重建可以被基于扩散的生成先验所替代，从而使本方法在真实场景中更具实用性。
英文原文摘要 1611 字符
Reconstructing a dynamic target moving over a large area is challenging. Standard approaches for dynamic object reconstruction require dense coverage in both the viewing space and the temporal dimension, typically relying on multi-view videos captured at each time step.However, such setups are only possible in constrained environments. In real-world scenarios, observations are often sparse over time and captured sparsely from diverse viewpoints (e.g., from security cameras), making dynamic reconstruction highly ill-posed. We present SV-GS, a framework that simultaneously estimates a deformation model and the object's motion over time under sparse observations. To initialize SV-GS, we leverage a rough skeleton graph and an initial static reconstruction as inputs to guide motion estimation. (Later, we show that this input requirement can be relaxed.) Our method optimizes a skeleton-driven deformation field composed of a coarse skeleton joint pose estimator and a module for fine-grained deformations. By making only the joint pose estimator time-dependent, our model enables smooth motion interpolation while preserving learned geometric details. Experiments on synthetic datasets show that our method outperforms existing approaches under sparse observations by up to 34% in PSNR, and achieves comparable performance to dense monocular video methods on real-world datasets despite using significantly fewer frames. Moreover, we demonstrate that the input initial static reconstruction can be replaced by a diffusion-based generative prior, making our method more practical for real-world scenarios.