trumans / pytorch3d.py
jnnan's picture
Upload 68 files
aeba71c verified
raw
history blame
8.39 kB
import functools
import torch
import torch.nn.functional as F
def quaternion_to_matrix(quaternions):
r, i, j, k = torch.unbind(quaternions, -1)
two_s = 2.0 / (quaternions * quaternions).sum(-1)
o = torch.stack(
(
1 - two_s * (j * j + k * k),
two_s * (i * j - k * r),
two_s * (i * k + j * r),
two_s * (i * j + k * r),
1 - two_s * (i * i + k * k),
two_s * (j * k - i * r),
two_s * (i * k - j * r),
two_s * (j * k + i * r),
1 - two_s * (i * i + j * j),
),
-1,
)
return o.reshape(quaternions.shape[:-1] + (3, 3))
def _copysign(a, b):
signs_differ = (a < 0) != (b < 0)
return torch.where(signs_differ, -a, a)
def _sqrt_positive_part(x: torch.Tensor) -> torch.Tensor:
ret = torch.zeros_like(x)
positive_mask = x > 0
ret[positive_mask] = torch.sqrt(x[positive_mask])
return ret
def matrix_to_quaternion(matrix: torch.Tensor) -> torch.Tensor:
if matrix.size(-1) != 3 or matrix.size(-2) != 3:
raise ValueError(f"Invalid rotation matrix shape f{matrix.shape}.")
batch_dim = matrix.shape[:-2]
m00, m01, m02, m10, m11, m12, m20, m21, m22 = torch.unbind(
matrix.reshape(*batch_dim, 9), dim=-1
)
q_abs = _sqrt_positive_part(
torch.stack(
[
1.0 + m00 + m11 + m22,
1.0 + m00 - m11 - m22,
1.0 - m00 + m11 - m22,
1.0 - m00 - m11 + m22,
],
dim=-1,
)
)
quat_by_rijk = torch.stack(
[
torch.stack([q_abs[..., 0] ** 2, m21 - m12, m02 - m20, m10 - m01], dim=-1),
torch.stack([m21 - m12, q_abs[..., 1] ** 2, m10 + m01, m02 + m20], dim=-1),
torch.stack([m02 - m20, m10 + m01, q_abs[..., 2] ** 2, m12 + m21], dim=-1),
torch.stack([m10 - m01, m20 + m02, m21 + m12, q_abs[..., 3] ** 2], dim=-1),
],
dim=-2,
)
quat_candidates = quat_by_rijk / (2.0 * q_abs[..., None].max(q_abs.new_tensor(0.1)))
return quat_candidates[
F.one_hot(q_abs.argmax(dim=-1), num_classes=4) > 0.5, :
].reshape(*batch_dim, 4)
def _axis_angle_rotation(axis: str, angle):
cos = torch.cos(angle)
sin = torch.sin(angle)
one = torch.ones_like(angle)
zero = torch.zeros_like(angle)
if axis == "X":
R_flat = (one, zero, zero, zero, cos, -sin, zero, sin, cos)
if axis == "Y":
R_flat = (cos, zero, sin, zero, one, zero, -sin, zero, cos)
if axis == "Z":
R_flat = (cos, -sin, zero, sin, cos, zero, zero, zero, one)
return torch.stack(R_flat, -1).reshape(angle.shape + (3, 3))
def euler_angles_to_matrix(euler_angles, convention: str):
if euler_angles.dim() == 0 or euler_angles.shape[-1] != 3:
raise ValueError("Invalid input euler angles.")
if len(convention) != 3:
raise ValueError("Convention must have 3 letters.")
if convention[1] in (convention[0], convention[2]):
raise ValueError(f"Invalid convention {convention}.")
for letter in convention:
if letter not in ("X", "Y", "Z"):
raise ValueError(f"Invalid letter {letter} in convention string.")
matrices = map(_axis_angle_rotation, convention, torch.unbind(euler_angles, -1))
return functools.reduce(torch.matmul, matrices)
def _angle_from_tan(
axis: str, other_axis: str, data, horizontal: bool, tait_bryan: bool
):
i1, i2 = {"X": (2, 1), "Y": (0, 2), "Z": (1, 0)}[axis]
if horizontal:
i2, i1 = i1, i2
even = (axis + other_axis) in ["XY", "YZ", "ZX"]
if horizontal == even:
return torch.atan2(data[..., i1], data[..., i2])
if tait_bryan:
return torch.atan2(-data[..., i2], data[..., i1])
return torch.atan2(data[..., i2], -data[..., i1])
def _index_from_letter(letter: str):
if letter == "X":
return 0
if letter == "Y":
return 1
if letter == "Z":
return 2
def matrix_to_euler_angles(matrix, convention: str):
if len(convention) != 3:
raise ValueError("Convention must have 3 letters.")
if convention[1] in (convention[0], convention[2]):
raise ValueError(f"Invalid convention {convention}.")
for letter in convention:
if letter not in ("X", "Y", "Z"):
raise ValueError(f"Invalid letter {letter} in convention string.")
if matrix.size(-1) != 3 or matrix.size(-2) != 3:
raise ValueError(f"Invalid rotation matrix shape f{matrix.shape}.")
i0 = _index_from_letter(convention[0])
i2 = _index_from_letter(convention[2])
tait_bryan = i0 != i2
if tait_bryan:
central_angle = torch.asin(
matrix[..., i0, i2] * (-1.0 if i0 - i2 in [-1, 2] else 1.0)
)
else:
central_angle = torch.acos(matrix[..., i0, i0])
o = (
_angle_from_tan(
convention[0], convention[1], matrix[..., i2], False, tait_bryan
),
central_angle,
_angle_from_tan(
convention[2], convention[1], matrix[..., i0, :], True, tait_bryan
),
)
return torch.stack(o, -1)
def standardize_quaternion(quaternions):
return torch.where(quaternions[..., 0:1] < 0, -quaternions, quaternions)
def quaternion_raw_multiply(a, b):
aw, ax, ay, az = torch.unbind(a, -1)
bw, bx, by, bz = torch.unbind(b, -1)
ow = aw * bw - ax * bx - ay * by - az * bz
ox = aw * bx + ax * bw + ay * bz - az * by
oy = aw * by - ax * bz + ay * bw + az * bx
oz = aw * bz + ax * by - ay * bx + az * bw
return torch.stack((ow, ox, oy, oz), -1)
def quaternion_multiply(a, b):
ab = quaternion_raw_multiply(a, b)
return standardize_quaternion(ab)
def quaternion_invert(quaternion):
return quaternion * quaternion.new_tensor([1, -1, -1, -1])
def quaternion_apply(quaternion, point):
if point.size(-1) != 3:
raise ValueError(f"Points are not in 3D, f{point.shape}.")
real_parts = point.new_zeros(point.shape[:-1] + (1,))
point_as_quaternion = torch.cat((real_parts, point), -1)
out = quaternion_raw_multiply(
quaternion_raw_multiply(quaternion, point_as_quaternion),
quaternion_invert(quaternion),
)
return out[..., 1:]
def axis_angle_to_matrix(axis_angle):
return quaternion_to_matrix(axis_angle_to_quaternion(axis_angle))
def matrix_to_axis_angle(matrix):
return quaternion_to_axis_angle(matrix_to_quaternion(matrix))
def axis_angle_to_quaternion(axis_angle):
angles = torch.norm(axis_angle, p=2, dim=-1, keepdim=True)
half_angles = 0.5 * angles
eps = 1e-6
small_angles = angles.abs() < eps
sin_half_angles_over_angles = torch.empty_like(angles)
sin_half_angles_over_angles[~small_angles] = (
torch.sin(half_angles[~small_angles]) / angles[~small_angles]
)
# for x small, sin(x/2) is about x/2 - (x/2)^3/6
# so sin(x/2)/x is about 1/2 - (x*x)/48
sin_half_angles_over_angles[small_angles] = (
0.5 - (angles[small_angles] * angles[small_angles]) / 48
)
quaternions = torch.cat(
[torch.cos(half_angles), axis_angle * sin_half_angles_over_angles], dim=-1
)
return quaternions
def quaternion_to_axis_angle(quaternions):
norms = torch.norm(quaternions[..., 1:], p=2, dim=-1, keepdim=True)
half_angles = torch.atan2(norms, quaternions[..., :1])
angles = 2 * half_angles
eps = 1e-6
small_angles = angles.abs() < eps
sin_half_angles_over_angles = torch.empty_like(angles)
sin_half_angles_over_angles[~small_angles] = (
torch.sin(half_angles[~small_angles]) / angles[~small_angles]
)
# for x small, sin(x/2) is about x/2 - (x/2)^3/6
# so sin(x/2)/x is about 1/2 - (x*x)/48
sin_half_angles_over_angles[small_angles] = (
0.5 - (angles[small_angles] * angles[small_angles]) / 48
)
return quaternions[..., 1:] / sin_half_angles_over_angles
def rotation_6d_to_matrix(d6: torch.Tensor) -> torch.Tensor:
a1, a2 = d6[..., :3], d6[..., 3:]
b1 = F.normalize(a1, dim=-1)
b2 = a2 - (b1 * a2).sum(-1, keepdim=True) * b1
b2 = F.normalize(b2, dim=-1)
b3 = torch.cross(b1, b2, dim=-1)
return torch.stack((b1, b2, b3), dim=-2)
def matrix_to_rotation_6d(matrix: torch.Tensor) -> torch.Tensor:
return matrix[..., :2, :].clone().reshape(*matrix.size()[:-2], 6)