pose and shape Parameter Space Sampling

[uestcjackey]

Hi，Thank you for providing the code，wonderful job.

I feel puzzled about the SMPL pose and shape param sampling mentioned in your paper section 5.1. Does uniform sampling means you not need to fit the CMU data as a mixed-gauss function, just to calculate the mean value and standard deviation to generate virtual shapes for every dims(usually as 10 dims)?

eg: numpy.random.uniform(low,high,size)

Do you provide any code or suggestion for this part? Thanks a lot.

[uestcjackey]

@williamljb any help will be appreciate， thks

[williamljb]

For the pose sampling I simply used the CMU MoCap dataset. For the shape sampling I used np.random.uniform(-3,3,[20])