search

namepllet / HandOccNet

Offical pytorch implementation of "HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network", CVPR 2022.
158 stars 31 forks source link

How is the feature map visualization got? #2

Open XiyueSun opened 2 years ago

XiyueSun commented 2 years ago

how to do the feature map visualization like figure 2 and 7?

namepllet commented 2 years ago

We apply absolute sum to make channel dimension 1, and show feature map from matpoltlib package.

jingyushi commented 2 years ago

@namepllet Hi, Park and Ou. Thanks for your impressive work. Could please also let me know how you obtained the Correlation Map as in Figure 4? I have now the 1x4x1024x1024 shape C from the matmul of Csoft and Csig. Thanks in advance!

namepllet commented 2 years ago

The correlation map in figure 4 shows correlation between single query(red point) and other keys.

So you can choose any query and reshape key dimension to 32x32 to visualize correlation map.

karta2155802 commented 2 years ago

Hi, I'm trying to visualize the primary feature map like figure 2 by following your method above with the demo model weight. But I couldn't get the same visualization as yours. Here's my code, input image and visualization results. Which part I did wrong?

        pfeats = primary_feats.abs().sum(dim=1).squeeze()

Thanks

namepllet commented 2 years ago

Since we refactored our code after paper submission, the feature map may look different.

And for the HO3D images, use pretrained model weight for HO3D. (The demo model is not trained on HO3D)