面向点云理解的双邻域图卷积方法
|
|
李宗民,徐畅,白云,鲜世洋,戎光彩
|
Dual-neighborhood graph convolution method for point cloud understanding
|
|
Zongmin LI,Chang XU,Yun BAI,Shiyang XIAN,Guangcai RONG
|
|
| 表 2 在ScanObjectNN基准上测试的分类结果 |
| Tab.2 Classification result on ScanObjectNN benchmark |
|
| 方法 | 年份 | mAcc/% | OA/% | | PointNet[7] | 2017 | 63.4 | 68.2 | | PointNet++[8] | 2017 | 75.4 | 77.9 | | DGCNN[13] | 2019 | 73.6 | 78.1 | | GBNet[20] | 2021 | 77.8 | 80.5 | | PointMLP[46] | 2022 | 84.4 | 85.7 | | RepSurf-U[21] | 2022 | 83.1 | 86.0 | | PointMLP+HyCoRe[43] | 2022 | 85.9 | 87.2 | | PointNeXT[42] | 2022 | 86.8 | 88.2 | | PointConT[44] | 2023 | 86.0 | 88.0 | | SPoTr[32] | 2023 | 86.8 | 88.6 | | DNG-Net(本文方法) | 2024 | 88.3 | 89.6 |
|
|
|