search

baegwangbin / MaGNet

[CVPR 2022 Oral] Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
MIT License
211 stars 15 forks source link

How to visualize sigma (uncertainty) with the same color map as that used in your paper? #10

Closed EchoTHChen closed 2 years ago

EchoTHChen commented 2 years ago

I cannot find the colormap similar to your paper in opencv-python. Could you share your visualization code about the sigma? Thanks!

baegwangbin commented 2 years ago

Hi, we used the 'Reds' colormap from matplotlib. You can do something like:

plt.imsave(target_image_path, predicted_sigma, cmap='Reds')

Note that predicted_sigma should be a NumPy float array with shape H X W.

EchoTHChen commented 2 years ago

Thanks