project SMPL vertices to 3d space with respective camera matrix

[friendly-code-bot]

Hi,

i would like to use your code for my research work but I encounter some problems and require some support.

My ultimate goal is to get the 3d coordinates of the vertices with my own camera matrix K. I want later on make selective body region selection and and need the 3d coordinates of the Human body to do so.

Acoording to your code, the SMPL vertices in the proxy representation and i would like to get the 3d coordinates somehow out of it.

Could you tell me how to do the projection from the proxy to the 3d coordinates using a specific camera matrix.

I would appreciate your help.

thanks

[chillcloud-dev]

following ...

[akashsengupta1997]

Hi,

Thanks for your interest in our work!

The vertex coordinates output by the SMPL model (line 116 of predict_poseMF_shapeGaussian_net.py) are in the SMPL world coordinate system. You can define your camera in this this coordinate system and project however you want. For example, in line 175 of the training code (train_poseMF_shapeGaussian_net.py), I set up a perspective camera in the SMPL world coordinates, and use that to project the SMPL 3D joints (in world coordinates) onto the image plane. Specifically, you may want to look at the perspective_project_torch function here:

HierarchicalProbabilistic3DHuman/utils/cam_utils.py

Line 30 in 9893133

def perspective_project_torch(points, rotation, translation, cam_K=None,

There is also an orthographic_project_torch function on the same file if you are using a scaled orthographic/weak perspective camera.

The proxy representation is not related to SMPL vertices. The proxy representation is the input representation consisting of 2D edge maps and 2D keypoint heatmaps.