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 1 在ModelNet40基准上测试的分类结果 |
| Tab.1 Classification result on ModelNet40 benchmark |
|
| 方法 | 年份 | mAcc/% | OA/% | | PointNet[7] | 2017 | 86.2 | 89.2 | | PointNet++[8] | 2017 | — | 91.9 | | KPConv[18] | 2019 | — | 92.9 | | DGCNN[13] | 2019 | 90.2 | 92.9 | | PointASNL[11] | 2020 | — | 92.9 | | PointTransformer[31] | 2020 | 90.6 | 93.7 | | PointMixer[40] | 2021 | 91.4 | 93.6 | | CurveNet[41] | 2021 | — | 93.8 | | PointNeXT[42] | 2022 | 91.1 | 94.0 | | DGCNN+HyCoRe[43] | 2022 | 91.0 | 93.7 | | PointConT[44] | 2023 | — | 93.5 | | MKConv[45] | 2023 | — | 93.7 | | DNG-Net(本文方法) | 2024 | 91.3 | 94.1 |
|
|
|