A simple question about camera and coordinate system.
See original GitHub issueHi, I have a simple question about ROMP. I have been struggling putting people into their correct relative position, but is it really possible using the root-aligned SMPL meshes without predicting their transl? (And if we have camera param K, will it be possible? )
-
What is the coordinate system of the vertices that are used for rendering? I think we are predicting camera coordinate system points but root-aligned, correct?
-
Following Q1, before rendering verts onto image, there is a trans added to verts (
'cam_trans in projection.py'
) What is it? and what isestimate_translation
actually doing? Is this estimating root’s position? https://github.com/Arthur151/ROMP/blob/e30b7d17f13089fa9fa114df494192e31b0f43ed/romp/lib/visualization/visualization.py#L61 -
I tried to replace the verts +trans in Q2 with GT mesh, so verts=GT_verts, without any other changes to your code, but the results are not correct, I expect it to be fully matched the person on the image but there are always shifts, and I also can’t use the same FOV otherwise it would be a very small mesh on the image.
Sorry if I understand anything wrong. I think rendering is the final part I didn’t understand in your code. Looking forward you for your answer!
Zhengdi
Issue Analytics
- State:
- Created a year ago
- Comments:24 (10 by maintainers)
Thanks! I will look into this, I do have the camera intrinsic.
Indeed! I got it, thx~