航天图像分割常缺标注，这论文用 SAM 3 自动生成伪标签，还解决了伪标签几何错误。TinyUNet 又小又快，边界指标提升明显。
GeoDistill-Refine 是一个两阶段框架，用离线 SAM 3 生成的伪掩码训练紧凑分割网络，无需人工标注。教师端融合 6 个固定提示，通过无权重 50% 投票稳定输出；学生先学前景轮廓，再用符号距离场、骨架和面积目标细化。在 SpaceSense-Bench HJM 上，相比普通伪标签学生，Image IoU 提升 0.0456，Boundary F1 提升 0.1380。部署用的 TinyUNet 只有 0.263M 参数，RTX 4090 上单张约 1.1ms。SPEED+ Lightbox、Sunlamp 和 TANGO 上的外部测试显示边界质量或前景精度有增益。
GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation
Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation. This paper presents GeoDistill-Refine, a two-stage framework that transfers offline SAM 3 pseudo-masks to a compact segmentation network. Six fixed prompts are fused by an unweighted 50% vote to stabilize the teacher output. The student first learns the foreground silhouette and is then refined with signed-distance-field, skeleton, and area objectives derived from the pseudo-mask. A sample-level gate, computed from prompt agreement, the valid-prompt ratio, and pseudo-mask area plausibility, reduces the influence of unreliable pseudo-geometry. On the SpaceSense-Bench HJM lockbox set, GeoDistill-Refine improves Image IoU and Boundary F1 by 0.0456 and 0.1380, respectively, over a plain pseudo-label student. External evaluations on the SPEED+ Lightbox and Sunlamp domains and on TANGO show competitive regional overlap together with gains in boundary quality or foreground precision. The deployed TinyUNet contains 0.263 M parameters and requires approximately 1.1 ms per image on an RTX 4090; SAM 3 pseudo-mask construction and the auxiliary geometry branches are used only during training.