VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Maps

2026-09-04

AI Summary

本文提出VoxelFix方法，通过基于图的模型直接从已完成的3D体素地图中纠正语义标签，提高地图准确性，用于解决自动构建语义3D地图中的错误问题。

Abstract

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.

Problem

• 3D semantic maps
• post-hoc correction
• semantic accuracy

Innovation

• post-hoc semantic correction
• graph-based model
• local geometry and neighboring semantic information