Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization

TL;DR

Cycle-Sync presents a robust, cycle-consistency-based framework for global camera pose estimation that outperforms existing methods and guarantees exact recovery without relying on inter-camera distances.

Contribution

We adapt message-passing least squares for camera location estimation emphasizing cycle consistency, providing the strongest deterministic recovery guarantees and robust outlier rejection.

Findings

Outperforms leading pose estimators on synthetic and real datasets

Achieves deterministic exact recovery with cycle consistency alone

Eliminates the need for bundle adjustment in global pose estimation

Abstract

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.