File size: 5,619 Bytes
01664b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
import torch
from torch.nn import functional as F

import numpy as np
from scipy.spatial.distance import cdist, euclidean

def geometric_median(X, eps=1e-5):
    y = np.mean(X, 0)

    while True:
        D = cdist(X, [y])
        nonzeros = (D != 0)[:, 0]

        Dinv = 1 / D[nonzeros]
        Dinvs = np.sum(Dinv)
        W = Dinv / Dinvs
        T = np.sum(W * X[nonzeros], 0)

        num_zeros = len(X) - np.sum(nonzeros)
        if num_zeros == 0:
            y1 = T
        elif num_zeros == len(X):
            return y
        else:
            R = (T - y) * Dinvs
            r = np.linalg.norm(R)
            rinv = 0 if r == 0 else num_zeros/r
            y1 = max(0, 1-rinv)*T + min(1, rinv)*y

        if euclidean(y, y1) < eps:
            return y1

        y = y1

#  Transformation code fomr pytorch3d https://pytorch3d.readthedocs.io/en/latest/_modules/pytorch3d/transforms/rotation_conversions.html#matrix_to_quaternion
def rotation_6d_to_matrix(d6: torch.Tensor) -> torch.Tensor:
    """
    Converts 6D rotation representation by Zhou et al. [1] to rotation matrix
    using Gram--Schmidt orthogonalization per Section B of [1].
    Args:
        d6: 6D rotation representation, of size (*, 6)

    Returns:
        batch of rotation matrices of size (*, 3, 3)

    [1] Zhou, Y., Barnes, C., Lu, J., Yang, J., & Li, H.
    On the Continuity of Rotation Representations in Neural Networks.
    IEEE Conference on Computer Vision and Pattern Recognition, 2019.
    Retrieved from http://arxiv.org/abs/1812.07035
    """

    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:
    """
    Converts rotation matrices to 6D rotation representation by Zhou et al. [1]
    by dropping the last row. Note that 6D representation is not unique.
    Args:
        matrix: batch of rotation matrices of size (*, 3, 3)

    Returns:
        6D rotation representation, of size (*, 6)

    [1] Zhou, Y., Barnes, C., Lu, J., Yang, J., & Li, H.
    On the Continuity of Rotation Representations in Neural Networks.
    IEEE Conference on Computer Vision and Pattern Recognition, 2019.
    Retrieved from http://arxiv.org/abs/1812.07035
    """
    batch_dim = matrix.size()[:-2]
    return matrix[..., :2, :].clone().reshape(batch_dim + (6,))

def _sqrt_positive_part(x: torch.Tensor) -> torch.Tensor:
    """
    Returns torch.sqrt(torch.max(0, x))
    but with a zero subgradient where x is 0.
    """
    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:
    """
    Convert rotations given as rotation matrices to quaternions.

    Args:
        matrix: Rotation matrices as tensor of shape (..., 3, 3).

    Returns:
        quaternions with real part first, as tensor of shape (..., 4).
    """
    if matrix.size(-1) != 3 or matrix.size(-2) != 3:
        raise ValueError(f"Invalid rotation matrix shape {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,
        )
    )

    # we produce the desired quaternion multiplied by each of r, i, j, k
    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,
    )

    # We floor here at 0.1 but the exact level is not important; if q_abs is small,
    # the candidate won't be picked.
    flr = torch.tensor(0.1).to(dtype=q_abs.dtype, device=q_abs.device)
    quat_candidates = quat_by_rijk / (2.0 * q_abs[..., None].max(flr))

    # if not for numerical problems, quat_candidates[i] should be same (up to a sign),
    # forall i; we pick the best-conditioned one (with the largest denominator)

    return quat_candidates[
        F.one_hot(q_abs.argmax(dim=-1), num_classes=4) > 0.5, :  # pyre-ignore[16]
    ].reshape(batch_dim + (4,))

def quaternion_to_matrix(quaternions: torch.Tensor) -> torch.Tensor:
    """
    Convert rotations given as quaternions to rotation matrices.

    Args:
        quaternions: quaternions with real part first,
            as tensor of shape (..., 4).

    Returns:
        Rotation matrices as tensor of shape (..., 3, 3).
    """
    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))