Shashikant Verma

No 'specMU' and 'specPC' key in generated 'FLAME_albedo_from_BFM.npz' File

1

The conversion from FLAME albedo from BFM generates only two components. Can you please suggest if I have a textured BFM mesh, How to convert it in the textured FLAME...

Unlabelled mask region in Flame.

1

  Do Flame not provide a mask for the region as shown in image 2. I have extracted and visualized all masks and the region below the ears (both...

SystemError: CPUDispatcher(<function _get_preds_fromhm at 0x7fc50e018440>) returned a result with an error set

2

installed using setup.py and, running ---> preds = fa.get_landmarks(input) gives error: TypeError: expected dtype object, got 'numpy.dtype[float32]' The above exception was the direct cause of the following exception: ``` Traceback...

GCNConv (or any) fails for input of type SparseTensor.

3

ASSUME a Pytorch geometric layer - Layer(x, edge-index)

I can't seem to find image sequence data on which various GIFs are generated. How to get these sequences? Are they part of crowd pose dataset?

Which version of tensorflow is used?

Thanks for sharing the code. Supplying shape parameters don't seem to have any effect. Following if else condition reads ```th_beta``` instead of default ```self.th_betas```, but rendering mesh does not have...

Please share from where to install psbody smpl module dependency?

Thanks for the great work. Can you please elaborate on how you divide up the volume into boxes? ``` def predefined_bbox(self, j, only_cur_index=False): if j == 15: xyz_min = np.array([-0.0901,...

Hi, Thanks for making this excellent dataset public! Since your SMPL's are not optimized for shape, we have garments that loosely/tightly fit the provided garment. If we want to optimize...