Load mesh from .obj file and check if it's watertight, also report boundary edges if it's not.

Args: dice: np.ndarray, (H, W, C), uint8 | Image.Image Returns: dice: np.ndarray, (H, W, C+1), uint8 | Image.Image

Converts supported cubemap formats to horizon params: - cubemap - cube_format (str): ('horizon', 'dice', 'dict', 'list') return:

Converts supported cubemap formats to horizon params: - cubemap - cube_format (str): ('horizon', 'dice', 'dict', 'list') return:

Converts panoramic RGBD data (image, distance, rays) into an Open3D mesh. Args: rgb: Input RGB image tensor (M, H, W, 3), uint8 or f

Converts panoramic RGBD data (image, distance, rays) into an Open3D mesh. Args: image: Input RGB image tensor (H, W, 3), uint8 or fl

Create rotation matrix at once" params: - roll, pitch, yaw (float): in radians - z_down (bool): flips pitch and yaw directions - dtyp

Create rotation matrix at once" params: - roll, pitch, yaw (float): in radians - z_down (bool): flips pitch and yaw directions - dtyp

Create rotation matrix NOTE: DEPRECATED

Create Rotation Matrix NOTE: DEPRECATED

e_img: ndarray in shape of [H, W, *] face_w: int, the length of each face of the cubemap

e_img: ndarray in shape of [H, W, *] fov_deg: scalar or (scalar, scalar) field of view in degree u_deg: horizon viewing angle in rang

0F 1R 2B 3L 4U 5D

Shape: - Input: :math:`(N, C, *)` where :math:`C=\text{num\_channels}` - Output: :math:`(N, C, *)` (same shape as input)

Shape: - Input: (B*M, C, H, W) or (B*M, C, HW) - Output: (B*M, C, H, W) or (B*M, C, HW)

Torch grid sampling algorithm params: - img (torch.Tensor) - grid (torch.Tensor) - out (Optional[torch.Tensor]): defaults to None

Numpy grid sampling algorithm params: - img (np.ndarray) - grid (np.ndarray) - out (np.ndarray) - mode (str): ('bilinear', 'bicub

Args: images: np.ndarray (B, 6, H, W, C) | torch.Tensor (B, 6, C, H, W) Returns: equis: np.ndarray, (B, H, W, C) dice

Torch Grid Sample (default) - Uses `torch.nn.functional.grid_sample` - By far the best way to sample params: - img (torch.Tensor): T

Convert a PyTorch tensor to a NumPy image.

Args: cube: torch.Tensor, [b*m, c, h, w] or [b, m, c, h, w] yaw: int

Args: cube: torch.Tensor [b*m, c, h, w] or [b, m, c, h, w] | np.ndarray, [b*m, h, w, c] or [b, m, h, w, c] shifts: int

Run Cube2Equi params: - horizon (torch.Tensor) - height, widht (int): output equirectangular image's size - mode (str) - backend

Run Cube2Equi params: - horizon (np.ndarray) - height, widht (int): output equirectangular image's size - mode (str) return: