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
Good question! In our previous work (METRO), we have studied both HRNet and ResNet50 as backbone. We found HRNet gives better reconstruction error, so we mainly use HRNet for the rest of experiments as well as Graphormer.
For your convenience, I show the table which was presented in our previous CVPR 2021 paper:
Thanks for your awesome work, hrnet-w64 is too heavy to inference on realtime, have you tried resnet-50. I wander it's performance.
Also, I noticed there is another paper(hand mesh) with git repo:https://github.com/SeanChenxy/HandMesh, which use resnet-18 as backbone.
Best!
The text was updated successfully, but these errors were encountered: