参考:https://blog.csdn.net/weixin_40766438/article/details/102969299
Scannet主页:http://www.scan-net.org/
github主页:GitHub - ScanNet/ScanNet
scannet数据集是一个二维三维数据集,主要采集了室内场景的二维图像信息,包括rgb、深度,三维点云ply数据,并进行了语义标签和实例标签标注。
完整数据集:一共1513个采集场景数据(每个场景中点云数量都不一样,如果要用到端到端可能需要采样,使每一个场景的点都相同),共21个类别的对象,其中,1201个场景用于训练,312个场景用于测试。
较小子集:由于2DRGB-D帧的数据量特别大,作者提供了下载较小子集的选项scannet_frames_25k(约25,000帧,从完整数据集中大约每100帧进行二次采样)通过ScanNet数据下载,有5.6G,还有基准评估scannet_frames_test这个,下图是下载scannet里面的
其中scannetV2即第二版本的scannet的结构和文件类型如下(存放在scans文件夹中):
<scanId>
|-- <scanId>_vh_clean.ply
(Updated if had remove annotations)
|-- <scanId>_vh_clean_2.ply
(Updated if had remove annotations)
|-- <scanId>.aggregation.json, <scanId>_vh_clean.aggregation.json
Updated aggregated instance-level semantic annotations on lo-res, hi-res meshes, respectively
|-- <scanId>_vh_clean_2.labels.ply
Updated visualization of aggregated semantic segmentation; colored by nyu40 labels (see legend referenced above; ply property 'label' denotes the ScanNet label id)
|-- <scanId>_2d-label.zip
Updated raw 2d projections of aggregated annotation labels as 16-bit pngs with ScanNet label ids
|-- <scanId>_2d-instance.zip
Updated raw 2d projections of aggregated annotation instances as 8-bit pngs
|-- <scanId>_2d-label-filt.zip
Updated filtered 2d projections of aggregated annotation labels as 16-bit pngs with ScanNet label ids
|-- <scanId>_2d-instance-filt.zip
Updated filtered 2d projections of aggregated annotation instances as 8-bit pngs
截图如下:
还有一个另外的文件:scannetv2-labels.combined.tsv
用meshlab打开其中的scene0000_00_vh_clean_2.ply,如下:(xxx_vh_clean.ply与其类似)
打开scene0000_00_ch_clean_2.labels.ply
做室内3d目标检测,往往会对数据处理,生成一个新的文件夹:scannet_train_detection_data
这个文件夹包含5类文件
ps:需要完整数据集可私信