GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Velentzas, Iason Georgios, Ahuja, Dhruv, Tsiotras, Panagiotis
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917550743355392
author Velentzas, Iason Georgios
Ahuja, Dhruv
Tsiotras, Panagiotis
author_facet Velentzas, Iason Georgios
Ahuja, Dhruv
Tsiotras, Panagiotis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00886
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation
Velentzas, Iason Georgios
Ahuja, Dhruv
Tsiotras, Panagiotis
Computer Vision and Pattern Recognition
Robotics
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.
title GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2606.00886