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

2025-11-04

AI Summary

This work addresses global camera pose estimation without distance priors. Methodologically, it proposes a synchronous algorithm grounded in enhanced cycle consistency: for the first time, cycle consistency is embedded into the Message-Passing Least Squares (MPLS) framework to jointly synchronize rotations and translations; a Welsch robust loss and a subspace-recovery-inspired outlier rejection module are integrated end-to-end with cycle constraints. Theoretically, it establishes the strongest deterministic exact recovery guarantee under the current lowest sample complexity. Experiments demonstrate state-of-the-art performance on both synthetic and real-world datasets—outperforming mainstream approaches including bundle adjustment—with superior robustness, global consistency, and computational efficiency.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

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.

Problem

• Robust global camera pose estimation framework
• Enhanced cycle-consistent synchronization for camera locations
• Deterministic exact-recovery guarantee without inter-camera distances

Innovation

• Adapts message-passing least squares for camera location estimation
• Redefines cycle consistency using iteratively estimated distances
• Integrates Welsch-type robust loss and outlier rejection module