面向密集预测任务的点云Transformer适配器

张德军,白燕子,曹锋,吴亦奇,徐战亚

Point cloud Transformer adapter for dense prediction task

Dejun ZHANG,Yanzi BAI,Feng CAO,Yiqi WU,Zhanya XU

表 2 S3DIS数据集(区域5)的语义分割结果

Tab.2 Semantic segmentation result of S3DIS dataset (area 5)

方法 mAcc/ % mIoU/ % mIoUcls/% 天花板 地板 墙壁 横梁 柱子 窗户 门 桌子 椅子 沙发 书柜 黑板 杂物 SPG[27] 66.5 58.0 89.4 96.9 78.1 0.0 42.8 48.9 61.6 84.7 75.4 69.8 52.6 2.1 52.2 PointWeb[2] 66.6 60.3 92.0 98.5 79.4 0.0 21.1 59.7 34.8 76.3 88.3 46.9 69.3 64.9 52.5 PAT[29] 70.8 60.1 93.0 98.5 72.3 1.0 41.5 85.1 38.2 57.7 83.6 48.1 67.0 61.3 33.6 PT[5] 76.5 70.4 94.0 98.5 86.3 0.0 38.0 63.4 74.3 89.1 82.4 74.3 80.2 76.0 59.3 PCT[6] 67.7 61.3 92.5 98.4 80.6 0.0 19.3 61.6 48.0 76.6 85.2 46.2 67.7 67.9 52.3 PatchF[13] — 67.3 91.8 98.7 86.2 0.0 34.1 48.9 62.4 81.6 89.8 47.2 74.9 74.4 58.6 PointCAT[28] 71.0 64.0 94.2 98.3 80.5 0.0 18.6 55.5 58.9 77.2 88.0 64.8 72.2 68.9 55.4 SPFormer[14] 77.3 68.9 91.5 98.2 81.4 0.0 23.3 65.3 40.0 75.5 87.7 59.5 67.8 65.6 49.4 Point-Bert[10] 75.7 63.5 91.3 92.3 73.1 0.0 33.9 65.6 60.4 76.5 82.7 86.8 64.0 41.7 43.0 PCT-Adapter 80.5 69.0 91.9 96.0 81.6 0.0 52.4 66.5 67.0 82.9 90.1 70.8 72.8 69.5 54.7