mask2former/utils/tranform.py

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))