You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have noticed the paper mentions a set of mask filtering processes for the MPM module. But I can't find the code related to that. How can I generate masks on my own datasets with the same mask filtering in the paper?
And also, will you provide the mask3d checkpoint with Mask scoring that you mention in the paper?
Thanks!
The text was updated successfully, but these errors were encountered:
Apologies for the delayed response—I was not very active due to submissions and being on annual leave.
The Mask Proposal Module (MPM) was inherently adapted from Mask3D. In the demo here, MPM is included to produce mask for our input pcd.
Regarding the benchmark results, to ensure a fair comparison with other works and ease of use—since many methods at the time of OpenIns3D followed similar strategies for mask proposal—we provided mask proposals directly.
If you want to generate masks organically, I recommend using Mask3D easy setup, as the mask results were originally obtained from there. Additionally, Segment3D appears to be a stronger version of the class-agnostic mask proposal.
Hi, Thanks for the great work!!
I have noticed the paper mentions a set of mask filtering processes for the MPM module. But I can't find the code related to that. How can I generate masks on my own datasets with the same mask filtering in the paper?
And also, will you provide the mask3d checkpoint with Mask scoring that you mention in the paper?
Thanks!
The text was updated successfully, but these errors were encountered: