VoxelFix: 完成済み3Dボクセルマップの事後セマンティック修正
VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Maps
完成済みの3Dボクセルマップのセマンティック精度を、幾何と占有状態を固定したままグラフベースモデルで修正する手法を提案し、mIoUを4.23〜5.00ポイント向上させた。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sunesh Praveen Raja Sundarasami, Taehyoung Kim, Johannes Scherer, Tomaž Cotič, Sivasubiramaniam Subbiah, Andreas Greiner, Paul Spannaus, Sebastian Houben
分類: cs.CV
原文アブストラクト
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.