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

NeurIPSSpotlight2025

Authors
Shaohan Li, Yunpeng Shi, Gilad Lerman
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

We introduce Cycle-Sync, a robust and global framework for estimating camera poses (both rotations and locations)

Opening excerpt from the authors’ abstract. source

Read the paper

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive