Closed tryhere closed 3 years ago
Thanks for your interest. We will release the supplementary materials recently or you can leave the email address, I will let you know when I publish it.
So is this paper submited for CVPR 2021, and when the code will be released? I also want to ask how to calculate the AP as there is no score. Is that use classification and the mask quality as SOLOv2? (I haven't read the code of CondIns)
Hi, thanks for your great work.
I have read CondInst but I am not familiar with instance segmentation on point cloud
.
I also want to know how I can find your supplementary materials.
I would be grateful if you could reply for me~
@Wei-i We will release an extended version recently. You can also leave your email, I can send it to you.
Thanks for your quick relpy. My email is chenwei1997@stu.xmu.edu.cn.
It may help me to understand some import details of DyCo3D implementation.
BTW, I am confused about some sentences below in this paper.
(1) During training, the ground truth for $C^z$ if it has the largest number of points in $C^z$.
What is the meaning of largets number of points
? For a predicted mask, doesn’t it only contain one specific category of mask?
(2) $\mathcal 1$ is an indicator function, showing the loss is only computed on the points that have identical semantic labels
with group $C^z$
From the paper, I think a cluster belongs to semantic prediction from Seg Head
and contains the points which belong to same semantic label. So it does not need an indicator function to determine whether a point have the identical semantic labels with group? But it seems I misunderstood.
@tonghe90 Do you release the extended version or supplementary materials? Or can you send it to my email? bitwqr@gmail.com
@qiruiw The extended version of Dyco3D can be found here: https://arxiv.org/abs/2107.08392, which includes the supplementary materials of Dyco3d
Thank you for your outstanding work! Where can I find your supplementary materials? I want to learn about the difference between your clustering algorithm and pointgroup~