Use the prediction result of SMPL to load that in Mesh lab

[JacobAtExp4531]

i am little confused in the output generated while passing the image features through the smpl model, I am getting 5 different arrays of values as prediction result. They are Joints,Vertices,Camera,Joints3D,Theta. The confusion is that which all things are required to save together as an object to load that in meshlab # Theta is the 85D vector holding [camera, pose, shape] # camera is 3D [s, tx, ty] # pose is 72D vector holding the rotation of 24 joints of SMPL in axis angle format # shape is 10D shape coefficients of SMPL

[akanazawa]

Hi,

You can take the vertices and the faces and save them to obj.