4D Primitive-Mache：粘合基元实现持久4D场景重建
4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstruction
把场景分解为一组随时间运动的刚性3D基元，并用稠密2D对应关系联合优化其刚体运动，为单目动态视频提供可回放的持久4D重建；其「基元+运动外推」思路可直接迁移到动态NeRF/高斯泼溅的时序一致性与遮挡补全问题。
原文依据 we decompose the scene into a set of rigid 3D primitives, which are assumed to be moving through the scene
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出4DPM，一个动态重建系统，它以一段随手拍摄的单目RGB视频为输入，输出场景完整且持久的重建结果。换言之，我们不仅重建场景当前可见的部分，也重建所有此前观察过的部分，从而能够在全部时间步上回放完整重建。我们的方法将场景分解为一组刚性3D基元，并假设这些基元在场景中运动。利用估计得到的稠密2D对应关系，我们通过一个优化流程联合推断这些基元的刚体运动，从而得到场景的4D重建，即提供随时间动态运动的三维几何。为实现这一点，我们还引入一种机制，对变为不可见的物体外推其运动，并采用运动分组技术以保持连续性。由此得到的系统具备4D时空感知能力，可支持诸如关节物体随时间的可回放三维重建、多物体扫描以及物体恒存性等能力。在物体扫描与多物体数据集上，我们的系统在定量与定性两方面均显著优于现有方法。
英文原文摘要 1218 字符
We present 4DPM, a dynamic reconstruction system that receives a casual monocular RGB video as input, and outputs a complete and persistent reconstruction of the scene. In other words, we reconstruct not only the currently visible parts of the scene, but also all previously viewed parts, which enables replaying the complete reconstruction across all timesteps. Our method decomposes the scene into a set of rigid 3D primitives, which are assumed to be moving through the scene. Using estimated dense 2D correspondences, we jointly infer the rigid motion of these primitives through an optimisation pipeline, yielding a 4D reconstruction of the scene, i.e. providing 3D geometry dynamically moving through time. To achieve this, we also introduce a mechanism to extrapolate motion for objects that become invisible, employing motion-grouping techniques to maintain continuity. The resulting system enables 4D spatio-temporal awareness, offering capabilities such as replayable 3D reconstructions of articulated objects through time, multi-object scanning, and object permanence. On object scanning and multi-object datasets, our system significantly outperforms existing methods both quantitatively and qualitatively.