Is depth from render_to_depth_image() consistent over frames ?

[alexs7]

Checklist

• [X] I have searched for similar issues.
• [X] For Python issues, I have tested with the latest development wheel.
• [X] I have checked the release documentation and the latest documentation (for master branch).

My Question

Hello,

Thanks for your work,

I think my question is related to: https://github.com/isl-org/Open3D/issues/2940

I wanted to ask about the depth values from OffscreenRenderer

That are acquired with: render_to_depth_image(). Are these depth values consistent across frames ? Meaning that if I use the depth value to reconstruct the 3D points, are those 3D points the same in the next frame ?

Imagine if I do so for all my frames and I collect all 3D points, and render them. Then I should see the global 3D model ?

[andrewcaunes]

I'm wondering this as well, can you get absolute depth values from the depth maps ?

[alexs7]

It's been a while, but I think I had to look at the source code and come to a conclusion. Also try getting the depth values for a couple of consecutive frames from SFM data.