Dynamic reconstruction has achieved remarkable progress, but there remain challenges in monocular input for more practical applications. The prevailing works attempt to construct efficient motion representations, but lack a unified spatiotemporal decomposition framework, suffering from either holistic temporal optimization or coupled hierarchical spatial composition. To this end, we propose WorldTree, a unified framework comprising Temporal Partition Tree (TPT) that enables coarse-to-fine optimization based on the inheritance-based partition tree structure for hierarchical temporal decomposition, and Spatial Ancestral Chains (SAC) that recursively query ancestral hierarchical structure to provide complementary spatial dynamics while specializing motion representations across ancestral nodes. Experimental results on different datasets indicate that our proposed method achieves 8.26% improvement of LPIPS on NVIDIA-LS and 9.09% improvement of mLPIPS on DyCheck compared to the second-best method. Code: https://github.com/iCVTEAM/WorldTree.

翻译：动态重建已取得显著进展，但在面向更实际应用的单目输入方面仍存在挑战。现有研究主要尝试构建高效的运动表征，但缺乏统一的时空分解框架，往往受限于整体时间优化或耦合的层次空间组合。为此，我们提出WorldTree这一统一框架，其包含基于继承式划分树结构实现层次时间分解的渐进优化时序划分树，以及通过递归查询祖先层次结构提供互补空间动态、同时在祖先节点间特化运动表征的空间祖先链。在不同数据集上的实验结果表明，相较于次优方法，我们提出的方法在NVIDIA-LS数据集上LPIPS指标提升8.26%，在DyCheck数据集上mLPIPS指标提升9.09%。代码：https://github.com/iCVTEAM/WorldTree。