Why is weight*1000 saved as uint16 images?

yindaz / DeepCompletionRelease

Deep Depth Completion of a Single RGB-D Image

http://deepcompletion.cs.princeton.edu/

563 stars 141 forks source link

Why is weight*1000 saved as uint16 images? #2

Closed hyf015 closed 6 years ago

hyf015 commented 6 years ago

Hi, I read your paper and like your work very much. When I was trying to read your code, I found this line: https://github.com/yindaz/DeepCompletionRelease/blob/922fc064bb8f480be1d8b31a1b8755eaea8fb268/matlab/GenerateOcclusionWeight.m#L14

If I understand correctly, in matlab MaxValue for uint16 images is 65535. May I know what's the point of weight*1000 here?

yindaz commented 6 years ago

You are correct this does not saturate the uint16 value range. This is just to reuse the image reading function that accepts 16bit PNG and usually 10^-3 accuracy is sufficient for optimization.

hyf015 commented 6 years ago

Thank you for your answer. I'll look into it.