用统一框架重建多时期场景，分离稳定与变化部分
ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
- 提出时序调制高斯表示，统一重建多个时期场景
- 在真实与合成数据上均优于基线，提升重建质量与时间一致性
- 适合长期监控、城市测绘等需追踪变化的场景研究
多时期图像集合在实际应用中普遍存在：城市重扫用于地图制作，工地定期回访以跟踪进度，自然区域持续监测环境变化。这类数据构成多时期场景，其几何与外观随时间演变。当前重建方法依赖不兼容假设：静态方法强制单一几何结构，动态方法假设平滑运动，二者在长期、非连续变化下均失效。为此，我们提出ChronoGS，一种时序调制高斯表示，可在统一锚定框架内重建所有时期。该方法可有效分离稳定与演化成分，实现多时期场景的时间一致重建。为推动相关研究，我们发布ChronoScene数据集，涵盖真实与合成多时期场景，捕捉几何与外观变化。实验表明，ChronoGS在重建质量与时间一致性方面持续优于基线。代码与数据集已公开于https://github.com/ZhongtaoWang/ChronoGS。
原文摘要 · Abstract (English)
Multi-period image collections are common in real-world applications. Cities are re-scanned for mapping, construction sites are revisited for progress tracking, and natural regions are monitored for environmental change. Such data form multi-period scenes, where geometry and appearance evolve. Reconstructing such scenes is an important yet underexplored problem. Existing pipelines rely on incompatible assumptions: static and in-the-wild methods enforce a single geometry, while dynamic ones assume smooth motion, both failing under long-term, discontinuous changes. To solve this problem, we introduce ChronoGS, a temporally modulated Gaussian representation that reconstructs all periods within a unified anchor scaffold. It's also designed to disentangle stable and evolving components, achieving temporally consistent reconstruction of multi-period scenes. To catalyze relevant research, we release ChronoScene dataset, a benchmark of real and synthetic multi-period scenes, capturing geometric and appearance variation. Experiments demonstrate that ChronoGS consistently outperforms baselines in reconstruction quality and temporal consistency. Our code and the ChronoScene dataset are publicly available at https://github.com/ZhongtaoWang/ChronoGS.
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。