How do I add pose to the clothed SMPL-X model? I tried to do this the following way, but did not succeed. I see that that the inferer.make_rotation_images() function calls the load_smplx() function, in which the SMPLX model along with its mesh vertices (in the variable smpl_output.vertices are obtained. The SMPLX model has the following variable attributes

vertices <class 'torch.Tensor'>, torch.Size([1, 10475, 3])
joints <class 'torch.Tensor'>, torch.Size([1, 127, 3])
full_pose <class 'NoneType'>, 
global_orient <class 'torch.Tensor'>, torch.Size([1, 3])
transl <class 'NoneType'>, 
betas <class 'torch.Tensor'>, torch.Size([1, 10])
body_pose <class 'torch.Tensor'>, torch.Size([1, 63])
left_hand_pose <class 'torch.Tensor'>, torch.Size([1, 45])
right_hand_pose <class 'torch.Tensor'>, torch.Size([1, 45])
expression <class 'torch.nn.parameter.Parameter'>, torch.Size([1, 10])
jaw_pose <class 'torch.Tensor'>, torch.Size([1, 3])

I tried assigning values to body_pose, left_hand_pose, and right_hand_pose. However, this does not modify smpl_output.vertices, and consequently, the generated output images are not modified.

I Download SMPL-X models from SMPL-X project page and move them to data/smplx/. But, unfortunately, I run into this trouble.

"Failed to interpret file %s as a pickle" % repr(file)) OSError: Failed to interpret file 'data/smplx/SMPLX_NEUTRAL.pkl' as a pickle

Could you give me a hand? Thanks~

Thank you for your contributions!

In the paper of StylePeople (Sec. 3.2 & supplementary material), you mention that the renderer network can be pretrained on 56 people from AzurePeople dataset. Based on my understanding, both neural texture and the weight of renderer network are unknown, jointly training the person-specific neural textures and a generalizable renderer network seems very hard and undeterminated. Could you please give more detailed instructions about how to pretrain the rendering network? Thank you so much!

I ran the render_azure_person.py script. I loaded the pose values from a different image. While the pose transfer is correct, I don't understand why the visualization of certain parts such as fingers is suffering from artifacts. See the example pasted below.

Left Side: Output on a standard SMPLX model; Right Side: Output on Clothed model (person_id=04). We can clearly see that the fingers are not well separated in the visualization. What is causing this and how to solve this problem?