Constructor

sh_coeff: [bz, 9, 3]

bbox from detector and landmarks are different

image: 0-255, uint8, rgb, [h, w, 3] return: detected box list

warp vertices from world space to uv space vertices: [bz, V, 3] uv_vertices: [bz, 3, h, w]

Computes the l1 loss between the ground truth keypoints and the predicted keypoints Inputs: kp_gt : N x K x 3 kp_pred: N x K x 2

Calculates the rotation matrices for a batch of rotation vectors Parameters ---------- rot_vecs: torch.tensor Nx3

Draw 68 key points Args: image: the input image kpt: (68, 3).

Calculates landmarks by barycentric interpolation Parameters ---------- vertices: torch.tensor BxVx3, dtype = torch.float32

normals: [bz, nv, 3] lights: [bz, nlight, 6] returns: shading: [bz, nv, 3]

3x3 convolution with padding

3x3 convolution with padding

r"""Function that returns Gaussian filter coefficients. Args: kernel_size (int): filter size. It should be odd and positive. sigm

Ref: https://github.com/facebookresearch/pytorch3d/blob/25c065e9dafa90163e7cec873dbb324a637c68b7/pytorch3d/io/obj_io.py Load a mesh from a file-l

Convert quaternion vector to angle axis of rotation. TODO: CORRECT Adapted from ceres C++ library: ceres-solver/include/ceres/rotation.h Arg

Convert quaternion coefficients to rotation matrix. Args: quat: size = [B, 4] 4 <===>(w, x, y, z) Returns: Rotation matrix cor

-- rendering shape with detail normal map

r"""Creates a binary kernel to extract the patches. If the window size is HxW will create a (H*W)xHxW kernel.

Selects the face contour depending on the reletive position of the head Input: vertices: N X num_of_vertices

vertices: [bz, nv, 3] lights: [bz, nlight, 6] returns: shading: [bz, nv, 3]

Convert an angle axis to a quaternion. Adapted from ceres C++ library: ceres-solver/include/ceres/rotation.h Args: angle_axis (torch

Applies a batch of rigid transformations to the joints Parameters ---------- rot_mats : torch.tensor BxNx3x3 Tensor of rotat

same as batch_matrix2axis Calculates the rotation matrices for a batch of rotation vectors Parameters ---------- rot_vec

Calculates the per vertex displacement due to the blend shapes Parameters ---------- betas : torch.tensor Bx(num_betas) Blend s

for batch image Args: image (torch.Tensor): the reference tensor of shape BXHxWXC. center: [bz, 2] bboxsize: [bz, 1]

Convert a flattened parameter vector to a dictionary of parameters code_dict.keys() = ['shape', 'tex', 'exp', 'pose', 'cam', 'light']

Convert displacement map into detail normal map

NOW validation

NOW validation

Get a yacs CfgNode object with default values for my_project.

r"""Function that returns Gaussian filter matrix coefficients. Args: kernel_size (Tuple[int, int]): filter sizes in the x and y direction

r"""Function that returns Gaussian filter matrix coefficients. Args: kernel_size (int): filter size should be odd. Returns:

r"""Function that returns Gaussian filter matrix coefficients. Args: kernel_size (int): filter size should be odd. Returns:

Performs Linear Blend Skinning with the given shape and pose parameters Parameters ---------- betas : torch.tensor BxNB