Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.18794 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917527423025152 |
|---|---|
| author | Wang, Zhongtao Dai, Jiaqi Zhu, Qingtian Li, Yilong Su, Mai Zhu, Fei Gai, Meng Wang, Shaorong Pan, Chengwei Chen, Yisong Wang, Guoping |
| author_facet | Wang, Zhongtao Dai, Jiaqi Zhu, Qingtian Li, Yilong Su, Mai Zhu, Fei Gai, Meng Wang, Shaorong Pan, Chengwei Chen, Yisong Wang, Guoping |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18794 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes Wang, Zhongtao Dai, Jiaqi Zhu, Qingtian Li, Yilong Su, Mai Zhu, Fei Gai, Meng Wang, Shaorong Pan, Chengwei Chen, Yisong Wang, Guoping Graphics Computer Vision and Pattern Recognition 68U05 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. |
| title | ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes |
| topic | Graphics Computer Vision and Pattern Recognition 68U05 |
| url | https://arxiv.org/abs/2511.18794 |