Event
Event-camera spacecraft pose estimation framework achieves 0.0474 on SPADES test set
1 reports · 1 sources
Yonglong Zhang and other authors submitted a paper preprint proposing a reliability-aware framework for spacecraft pose estimation based on event cameras, which chains together polarity-time localization, geometric recovery, event-CAD refinement, and trajectory optimization, and uses a three-branch representation of positive events, negative events, and recent-event temporal sequences. The authors report that on the official SPADES challenge test set, the complete system achieves a composite pose score of 0.0474, about 5.4% lower than PASAN+IRIS. Ablation results show that basic localization plus uniform PnP scores 0.0772, and the complete cascade reduces it to 0.0514; under the same single-frame observations, quality weighting reduces the score from 0.0549 with constant-weight optimization to 0.0514.
Report timeline
- Polarity-Time Interaction and Multi-Level Reliability for Event-Based Spacecraft Pose Estimation
This study proposes a reliability-aware framework that connects polarity-time localization, geometric recovery, event-CAD refinement, and trajectory optimization in sequence, using a three-branch representation that combines positive events, negative events, and recent-event timing. On the official SPADES challenge test set, the complete system achieves a combined pose score of 0.0474, about 5.4% lower than PASAN+IRIS. Ablations show that base localization with uniform PnP scores 0.0772, while the full cascade reduces it to 0.0514; under identical single-frame observations, quality weighting lowers the score from 0.0549 to 0.0514.
arXiv cs.RO ·