Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.02329 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914134221651968 |
|---|---|
| author | Li, Shaohan Shi, Yunpeng Lerman, Gilad |
| author_facet | Li, Shaohan Shi, Yunpeng Lerman, Gilad |
| contents | We introduce Cycle-Sync, a robust and global framework for estimating camera poses (both rotations and locations). Our core innovation is a location solver that adapts message-passing least squares (MPLS) -- originally developed for group synchronization -- to camera location estimation. We modify MPLS to emphasize cycle-consistent information, redefine cycle consistencies using estimated distances from previous iterations, and incorporate a Welsch-type robust loss. We establish the strongest known deterministic exact-recovery guarantee for camera location estimation, showing that cycle consistency alone -- without access to inter-camera distances -- suffices to achieve the lowest sample complexity currently known. To further enhance robustness, we introduce a plug-and-play outlier rejection module inspired by robust subspace recovery, and we fully integrate cycle consistency into MPLS for rotation synchronization. Our global approach avoids the need for bundle adjustment. Experiments on synthetic and real datasets show that Cycle-Sync consistently outperforms leading pose estimators, including full structure-from-motion pipelines with bundle adjustment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization Li, Shaohan Shi, Yunpeng Lerman, Gilad Computer Vision and Pattern Recognition Numerical Analysis Robotics Methodology 90C26, 90C17, 68Q87, 65C20, 90-08, 60-08 G.1.6; I.4.0 We introduce Cycle-Sync, a robust and global framework for estimating camera poses (both rotations and locations). Our core innovation is a location solver that adapts message-passing least squares (MPLS) -- originally developed for group synchronization -- to camera location estimation. We modify MPLS to emphasize cycle-consistent information, redefine cycle consistencies using estimated distances from previous iterations, and incorporate a Welsch-type robust loss. We establish the strongest known deterministic exact-recovery guarantee for camera location estimation, showing that cycle consistency alone -- without access to inter-camera distances -- suffices to achieve the lowest sample complexity currently known. To further enhance robustness, we introduce a plug-and-play outlier rejection module inspired by robust subspace recovery, and we fully integrate cycle consistency into MPLS for rotation synchronization. Our global approach avoids the need for bundle adjustment. Experiments on synthetic and real datasets show that Cycle-Sync consistently outperforms leading pose estimators, including full structure-from-motion pipelines with bundle adjustment. |
| title | Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization |
| topic | Computer Vision and Pattern Recognition Numerical Analysis Robotics Methodology 90C26, 90C17, 68Q87, 65C20, 90-08, 60-08 G.1.6; I.4.0 |
| url | https://arxiv.org/abs/2511.02329 |