Since there are no public benchmarks for point cloud upsampling, we collect a dataset of 60 different models from the Visionair repository. ... We randomly select 40 for training, and use the rest for testing.
训练数据集:Visionair repository
.OFF
下载地址:https://github.com/yulequan/PU-Net readme 中
特点:网格质量较高,完整,没有孔等
测试数据集:ModelNet40
.OFF、ShapeNet
.PTS
vcg
版本算法实现中,读取的是 PLY 文件。且 PLY 文件中 edge、face 数量为 0。
CGAL
版本算法实现中,可读取多种格式。
程序可处理的数据格式:
vcg
版本 .PLY - https://www.dropbox.com/s/qb1sf04efa829nz/Point Cloud Procesing 1.0.zip?dl=0CGAL
版本 .XYZ、.OFF、.PLY、.LAS。- http://doc.cgal.org/latest/Point_set_processing_3/数据格式:.OFF
数据特点:点云规整,质量较高
部分样例:
[pic_1]
数据格式:.OFF
数据特点:结构简单,不适合做点云数据集,模型结构更多通过边来体现
部分样例:
[pic_2]
This dataset provides part segmentation to a subset of ShapeNetCore models, containing ~16K models from 16 shape categories. The number of parts for each category varies from 2 to 6 and there are a total number of 50 parts.
数据格式:.PTS
数据特点:纯点集,有类型标注,点云较为稀疏
部分样例:
[pic_3]
原文:https://www.cnblogs.com/crayonsea/p/12819514.html