TRI-ML/packnet-sfm

When estimating depth maps, RGB images and 3-channel grayscale images, which is more conducive to predicting accurate depth maps as input# Update

hutingz opened this issue · 0 comments

    # Update

So I have tried with my custom dataset again. This time the data is RGB instead of 3-channel grayscale image. This looks good.

Your work is amazing.

Kudos!

Screenshot from 2020-11-26 10-00-11
Screenshot from 2020-11-26 10-00-27

Originally posted by @surfii3z in #94 (comment)