liuzhengzhe
commented
2 years ago Hi, the segment is our super voxel. We annotate the points, and then propagate the annotated point to the whole super voxel it belongs to.
Please note that the super voxel propagation itself may cause some error (it not happen in scannet, but happen in S3DIS).
argosdh @.***> 于2021年11月12日周五 下午6:57写道：
Hi, I was checking the code. I found out that you choose the random segment of each instance to be annotated( https://github.com/liuzhengzhe/One-Thing-One-Click/blob/6b452493727e8fe813c85a97e6e1876767c4c053/data/prepare_data_otoc.py#L95). And at the end of this function you set all points in this segment to be annotated. For example, at scene0000_00, there are 67 instances in total, from my perspective, only 67 points should be annotated. I calculated len(np.where(sem_labels!=-100)[0]) for this scan and I found that there are 15468 points with label. I also visualized the point cloud and found it is very different from figure in paper. I think what the code did is keeping one segment of each instance but not keeping only one single point of it. Is this because later you need to propagate the one labled point to the corresponding super voxel(as segment now). So this operation is equivalent to what I described above?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/liuzhengzhe/One-Thing-One-Click/issues/13, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB7WPDBI4VIWYF4LCJSM2CDULTXJ5ANCNFSM5H4SCIXA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
argosdh
Hi, I was checking the code. I found out that you choose the random segment of each instance to be annotated(https://github.com/liuzhengzhe/One-Thing-One-Click/blob/6b452493727e8fe813c85a97e6e1876767c4c053/data/prepare_data_otoc.py#L95). And at the end of this function you set all points in this segment to be annotated. For example, at scene0000_00, there are 67 instances in total, from my perspective, only 67 points should be annotated. I calculated len(np.where(sem_labels!=-100)[0]) for this scan and I found that there are 15468 points with label. I also visualized the point cloud and found it is very different from figure in paper. I think what the code did is keeping one segment of each instance but not keeping only one single point of it. Is this because later you need to propagate the one labled point to the corresponding super voxel(as segment now). So this operation is equivalent to what I described above?