RegTR
RegTR copied to clipboard
How to get the image result of Visualization of attention?
Hi, Zi Jian:
Thanks for sharing so nice work. Could you mind sharing the method to reproduce your results for Visualization of attention? Just as presented by Fig5. and Fig6. from your paper?
Fig 5 does not show the attention but visualizes the locations of the keypoints and their corresponding locations. The network outputs all of these quantities so it should be quite easy to visualize them, and I have already provided a function to draw them here.
The attention weights are shown in Fig 6. For this, you need to first retrieve the attention weights, which can be obtained via the provided get_attentions()
function here. After that, you can just colorize the point cloud using the weights of a particular point.
Ok, thanks for your patient reply. I will have a try.