GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation

2026-05-30

AI Summary

This study addresses the challenge of drastic appearance variations in spacecraft imagery caused by harsh space lighting conditions and the limited generalization capability of existing segmentation models. To this end, the authors propose GABI, a lightweight boundary-aware multi-task segmentation architecture. GABI incorporates a distance field prediction head into a convolutional backbone, leveraging geometric priors to enhance boundary perception while maintaining low computational complexity and improving structural spatial consistency. Experimental results on the SPARK benchmark demonstrate that GABI achieves a 5% average precision gain and surpasses baseline methods by over 50% in cross-domain generalization. Its lightweight variant matches the performance of heavyweight Transformer-based models in terms of IoU and F1 score with approximately tenfold fewer parameters, while its heavier version delivers superior accuracy with a model size nearly three times smaller.

Abstract

Accurate segmentation is crucial for autonomous spacecraft, as it directly affects downstream tasks related to 3D situational awareness. The harsh illumination conditions of space, however, produce images with high variability in appearance, hindering the generalization of segmentation approaches across different spacecraft and environments. In this work, we propose GABI, a lightweight boundary-aware multi-task segmentation architecture that augments a convolutional backbone with an auxiliary distance-field prediction head. The distance field provides dense geometric supervision around object boundaries, encouraging the network to learn spatially consistent representations of spacecraft structures while maintaining low model complexity suitable for onboard perception systems. We evaluated GABI against both an established convolutional baseline and a heavier transformer-based architecture. On the SPARK benchmark, distance-field supervision improves the baseline by up to $5\%$ in Average Precision while achieving performance comparable to the transformer models. In generalization experiments, GABI improves Average Precision by more than $50\%$ over the baseline. In cross-domain evaluation, the lightweight GABI variant performs within $5\%$ in IoU and F1-score of the heavier transformer model while being approximately ten times smaller. At the same time, the heavier GABI variant surpasses the transformer architectures while remaining nearly three times lighter.

Problem

• spacecraft segmentation
• generalization
• harsh illumination
• 3D situational awareness
• cross-domain

Innovation

• distance-field supervision
• boundary-aware segmentation
• lightweight architecture
• spacecraft segmentation
• geometric consistency