medusa.recon.flame.lbs#

Module with functionality for linear blend skinning.

See ./deca/license.md for conditions for use.

Module Contents#

medusa.recon.flame.lbs.rot_mat_to_euler(rot_mats)[source]#
medusa.recon.flame.lbs.lbs(betas, pose, v_template, shapedirs, posedirs, J_regressor, parents, lbs_weights, pose2rot=True)[source]#

Performs Linear Blend Skinning with the given shape and pose parameters.

Parameters:

  • betas (torch.tensor BxNB) – The tensor of shape parameters

  • pose (torch.tensor Bx(J + 1) * 3) – The pose parameters in axis-angle format

  • BxVx3 (v_template torch.tensor) – The template mesh that will be deformed

  • shapedirs (torch.tensor 1xNB) – The tensor of PCA shape displacements

  • posedirs (torch.tensor Px(V * 3)) – The pose PCA coefficients

  • J_regressor (torch.tensor JxV) – The regressor array that is used to calculate the joints from the position of the vertices

  • parents (torch.tensor J) – The array that describes the kinematic tree for the model

  • lbs_weights (torch.tensor N x V x (J + 1)) – The linear blend skinning weights that represent how much the rotation matrix of each part affects each vertex

  • pose2rot (bool, optional) – Flag on whether to convert the input pose tensor to rotation matrices. The default value is True. If False, then the pose tensor should already contain rotation matrices and have a size of Bx(J + 1)x9

  • dtype (torch.dtype, optional) –

Returns:

  • verts (torch.tensor BxVx3) – The vertices of the mesh after applying the shape and pose displacements.

  • joints (torch.tensor BxJx3) – The joints of the model

medusa.recon.flame.lbs.blend_shapes(betas, shape_disps)[source]#

Calculates the per vertex displacement due to the blend shapes.

Parameters:

  • betas (torch.tensor Bx(num_betas)) – Blend shape coefficients

  • shape_disps (torch.tensor Vx3x(num_betas)) – Blend shapes

Returns:

The per-vertex displacement due to shape deformation

Return type:

torch.tensor BxVx3

medusa.recon.flame.lbs.batch_rodrigues(rot_vecs, epsilon=1e-08)[source]#

Calculates the rotation matrices for a batch of rotation vectors :param rot_vecs: array of N axis-angle vectors :type rot_vecs: torch.tensor Nx3

Returns:

R – The rotation matrices for the given axis-angle parameters

Return type:

torch.tensor Nx3x3

medusa.recon.flame.lbs.transform_mat(R, t)[source]#

Creates a batch of transformation matrices :param - R: Bx3x3 array of a batch of rotation matrices :param - t: Bx3x1 array of a batch of translation vectors

Returns:

Bx4x4 Transformation matrix

Return type:

  • T

medusa.recon.flame.lbs.batch_rigid_transform(rot_mats, joints, parents)[source]#

Applies a batch of rigid transformations to the joints.

Parameters:

  • rot_mats (torch.tensor BxNx3x3) – Tensor of rotation matrices

  • joints (torch.tensor BxNx3) – Locations of joints

  • parents (torch.tensor BxN) – The kinematic tree of each object

  • dtype (torch.dtype, optional:) – The data type of the created tensors, the default is torch.float32

Returns:

  • posed_joints (torch.tensor BxNx3) – The locations of the joints after applying the pose rotations

  • rel_transforms (torch.tensor BxNx4x4) – The relative (with respect to the root joint) rigid transformations for all the joints