How is this reading the depth image

[ArghyaChatterjee]

Hello,

I am trying to implement this on my own dataset with a zedmini. The problem is that I don't see the depth image visually that you provided as part of the default test (Mustard bottle from YCBvideo dataset).

Here is the data for the YCBVideo:

1. RGB image (640x360):

2. Depth image (640x360, ??, size=49.9 kb):

Here is a data from my custom dataset of mug:

1. RGB image (672x376):

2. Depth Image (672x376, 16 bit, size=149.9 kb):

Will this pose any issue for pose estimation with foundation pose?

[QazyBi]

To visualize the depth image, you can convert it into a grayscale image