VoxelFix：对完成的3D体素图进行事后语义校正

中文摘要 AI 辅助

语义3D地图正越来越多地通过将学习到的语义预测集成到3D表示中，为航空机器人自动构建，这避免了成本高昂的手动3D标注，但感知和建图流程中的错误仍会保留在生成的地图中，降低其对下游自主任务的可靠性。现有3D语义地图优化方法要么依赖原始观测，要么将占用视为预测问题的一部分，要么对完成的地图应用非学习型局部正则化。相反，我们研究事后语义校正，探究能否在保持完成地图的几何结构和占用状态固定的情况下，直接从该地图恢复语义准确性。我们提出VoxelFix，一种基于图的模型，其根据局部几何结构和相邻语义信息校正体素标签。为获取训练对，我们根据上游地图中观察到的类别混淆情况，对标注的OccuFly地图的连续区域进行破坏。我们在由四个独立训练的2D分割模型的预测生成的完成OccuFly地图上评估VoxelFix，该模型可将平均交并比（mIoU）稳定提升4.23至5.00个百分点，增益广泛分布于所有评估的语义类别中，对树木、屋顶和墙壁的提升尤为显著。在独立重建的分布外航空场景上的结果进一步表明，所学的校正方法可在训练时未见的环境中实现迁移。

英文摘要

Semantic 3D maps are increasingly constructed automatically for aerial robotics by integrating learned semantic predictions into 3D representations. While this avoids costly manual 3D annotation, errors in the perception and mapping pipeline can persist in the resulting map, reducing its reliability for downstream autonomous tasks. Existing 3D semantic map refinement methods either rely on the original observations, treat occupancy as part of the prediction problem, or apply non-learned local regularization to completed maps. Instead, we study post-hoc semantic correction, asking whether semantic accuracy can be recovered directly from the completed map while keeping its geometry and occupancy fixed. We introduce \method, a graph-based model that corrects voxel labels based on local geometry and neighboring semantic information. To obtain training pairs, we corrupt contiguous regions of annotated OccuFly maps according to class confusions observed in upstream maps. We evaluate \method on completed OccuFly maps generated from predictions of four independently trained 2D segmentation models. \method consistently improves mIoU by 4.23--5.00 percentage points, with gains broadly distributed across the evaluated semantic classes and particularly strong improvements for tree, roof, and wall. Results on an independently reconstructed out-of-distribution aerial scene further suggest that the learned correction can transfer beyond the environments seen during training.

发表机构

• Fraunhofer IVI（弗劳恩霍夫应用研究促进协会下属IVI研究所）
• Hochschule Bonn-Rhein-Sieg（波恩-莱茵-锡格应用科学大学）
• University of Bologna（博洛尼亚大学）
• FAU（弗里德里希-亚历山大-埃尔朗根-纽伦堡大学）
• THI（应用科学大学伊尔默瑙）

机构由 AI 辅助整理，请以论文原文为准。