MANO

MANO is a skinned hand model with shape and articulated finger pose parameters.

Setup

MANO requires registration at https://mano.is.tue.mpg.de/.

# Download MANO after configuring credentials for the upstream site.
body-models download mano

Manual paths can also be configured per side:

# Configure local MANO files when you do not want the downloader to manage them.
body-models set mano-right /path/to/MANO_RIGHT.pkl
body-models set mano-left /path/to/MANO_LEFT.pkl

API

body_models.parts.mano.numpy.MANO

MANO(
    model_path=None,
    side=None,
    flat_hand_mean=False,
    simplify=1.0,
    rotation_type="axis_angle",
    kernel="numpy",
)

Bases: BodyModel

MANO hand model with NumPy backend.

Initialize the MANO model.

PARAMETER	DESCRIPTION
model_path	Path to model assets, or the default assets when omitted. TYPE: Path | str | None DEFAULT: None
side	Hand side to load. TYPE: Literal['right', 'left'] | None DEFAULT: None
flat_hand_mean	Whether to use a flat hand as the pose mean. TYPE: bool DEFAULT: False
simplify	Mesh simplification factor to apply while loading. TYPE: float DEFAULT: 1.0
rotation_type	Rotation representation expected by pose inputs. TYPE: RotationType DEFAULT: 'axis_angle'
kernel	Backend kernel used for forward evaluation. TYPE: Literal['numpy', 'scipy', 'numba'] DEFAULT: 'numpy'

METHOD	DESCRIPTION
forward_vertices	Compute posed mesh vertices.
forward_skeleton	Compute posed joint transforms.
prepare_identity	Precompute shape-dependent state for repeated forward passes.
prepare_pose	Precompute pose-dependent state for repeated forward passes.
joint_index	Resolve a standard joint to this model's native joint index.
get_tpose	Get parameters for the SMPL-style T-pose.
get_apose	Get parameters for the MHR-style A-pose.
prepare_skinning	Pack prepared model state into renderer-ready skinning inputs.

Source code in src/body_models/parts/mano/numpy.py

def __init__(
    self,
    model_path: Path | str | None = None,
    side: Literal["right", "left"] | None = None,
    flat_hand_mean: bool = False,
    simplify: float = 1.0,
    rotation_type: RotationType = "axis_angle",
    kernel: Literal["numpy", "scipy", "numba"] = "numpy",
):
    """Initialize the MANO model.

    Args:
        model_path: Path to model assets, or the default assets when omitted.
        side: Hand side to load.
        flat_hand_mean: Whether to use a flat hand as the pose mean.
        simplify: Mesh simplification factor to apply while loading.
        rotation_type: Rotation representation expected by pose inputs.
        kernel: Backend kernel used for forward evaluation.
    """
    if side is not None and side not in ("right", "left"):
        raise ValueError(f"Invalid side: {side}. Must be 'right' or 'left'.")
    if rotation_type not in VALID_ROTATION_TYPES:
        raise ValueError(f"Invalid rotation_type: {rotation_type}")
    if simplify < 1.0:
        raise ValueError("simplify must be >= 1.0")
    if kernel not in self.kernels:
        raise ValueError(f"Invalid kernel: {kernel}")

    self.side = side if side is not None else "right"
    self.rotation_type = rotation_type
    self.num_rot_dims = 2 if rotation_type in ("matrix", "rotmat") else 1
    self._kernel = _get_kernel(kernel)

    resolved_path = get_model_path(model_path, side)
    self.weights = load_model_data(resolved_path, flat_hand_mean=flat_hand_mean, simplify=simplify)

forward_vertices

forward_vertices(
    hand_pose,
    wrist_rotation=None,
    global_rotation=None,
    global_translation=None,
    vertex_indices=None,
    *,
    shape=None,
    identity=None,
)

Compute posed mesh vertices.

PARAMETER	DESCRIPTION
hand_pose	Local hand joint rotations. TYPE: Float[ndarray, 'B 15 N'] | Float[ndarray, 'B 15 3 3']
wrist_rotation	Root wrist rotation. TYPE: Float[ndarray, 'B N'] | Float[ndarray, 'B 3 3'] | None DEFAULT: None
global_rotation	Global model rotation. TYPE: Float[ndarray, 'B N'] | Float[ndarray, 'B 3 3'] | None DEFAULT: None
global_translation	Global model translation. TYPE: Float[ndarray, 'B 3'] | None DEFAULT: None
vertex_indices	Optional subset of vertices to return. TYPE: Any | None DEFAULT: None
shape	Shape coefficients. TYPE: Float[ndarray, '*batch 10'] | None DEFAULT: None
identity	Optional output from :meth:prepare_identity. TYPE: ManoIdentity | None DEFAULT: None

RETURNS	DESCRIPTION
Float[ndarray, 'B V 3']	Posed vertex positions.

Source code in src/body_models/parts/mano/numpy.py

def forward_vertices(
    self,
    hand_pose: Float[np.ndarray, "B 15 N"] | Float[np.ndarray, "B 15 3 3"],
    wrist_rotation: Float[np.ndarray, "B N"] | Float[np.ndarray, "B 3 3"] | None = None,
    global_rotation: Float[np.ndarray, "B N"] | Float[np.ndarray, "B 3 3"] | None = None,
    global_translation: Float[np.ndarray, "B 3"] | None = None,
    vertex_indices: Any | None = None,
    *,
    shape: Float[np.ndarray, "*batch 10"] | None = None,
    identity: ManoIdentity | None = None,
) -> Float[np.ndarray, "B V 3"]:
    """Compute posed mesh vertices.

    Args:
        hand_pose: Local hand joint rotations.
        wrist_rotation: Root wrist rotation.
        global_rotation: Global model rotation.
        global_translation: Global model translation.
        vertex_indices: Optional subset of vertices to return.
        shape: Shape coefficients.
        identity: Optional output from :meth:`prepare_identity`.

    Returns:
        Posed vertex positions.
    """
    if identity is None:
        assert shape is not None
        batch_shape = tuple(hand_pose.shape[: -(self.num_rot_dims + 1)])
        identity = self.prepare_identity(np.broadcast_to(shape, (*batch_shape, shape.shape[-1])))
    pose = self.prepare_pose(hand_pose, wrist_rotation, identity=identity)
    return self._kernel.forward_vertices(
        self.weights,
        identity["rest_vertices"],
        pose["skinning_transforms"],
        pose["pose_offsets"],
        global_rotation=global_rotation,
        global_translation=global_translation,
        vertex_indices=vertex_indices,
        rotation_type=self.rotation_type,
    )

forward_skeleton

forward_skeleton(
    hand_pose,
    wrist_rotation=None,
    global_rotation=None,
    global_translation=None,
    joint_indices=None,
    *,
    shape=None,
    identity=None,
)

Compute posed joint transforms.

PARAMETER	DESCRIPTION
hand_pose	Local hand joint rotations. TYPE: Float[ndarray, 'B 15 N'] | Float[ndarray, 'B 15 3 3']
wrist_rotation	Root wrist rotation. TYPE: Float[ndarray, 'B N'] | Float[ndarray, 'B 3 3'] | None DEFAULT: None
global_rotation	Global model rotation. TYPE: Float[ndarray, 'B N'] | Float[ndarray, 'B 3 3'] | None DEFAULT: None
global_translation	Global model translation. TYPE: Float[ndarray, 'B 3'] | None DEFAULT: None
joint_indices	Optional subset of joints to return. TYPE: Any | None DEFAULT: None
shape	Shape coefficients. TYPE: Float[ndarray, '*batch 10'] | None DEFAULT: None
identity	Optional output from :meth:prepare_identity. TYPE: ManoIdentity | None DEFAULT: None

RETURNS	DESCRIPTION
Float[ndarray, 'B 16 4 4']	Joint transforms in the model hierarchy.

Source code in src/body_models/parts/mano/numpy.py

def forward_skeleton(
    self,
    hand_pose: Float[np.ndarray, "B 15 N"] | Float[np.ndarray, "B 15 3 3"],
    wrist_rotation: Float[np.ndarray, "B N"] | Float[np.ndarray, "B 3 3"] | None = None,
    global_rotation: Float[np.ndarray, "B N"] | Float[np.ndarray, "B 3 3"] | None = None,
    global_translation: Float[np.ndarray, "B 3"] | None = None,
    joint_indices: Any | None = None,
    *,
    shape: Float[np.ndarray, "*batch 10"] | None = None,
    identity: ManoIdentity | None = None,
) -> Float[np.ndarray, "B 16 4 4"]:
    """Compute posed joint transforms.

    Args:
        hand_pose: Local hand joint rotations.
        wrist_rotation: Root wrist rotation.
        global_rotation: Global model rotation.
        global_translation: Global model translation.
        joint_indices: Optional subset of joints to return.
        shape: Shape coefficients.
        identity: Optional output from :meth:`prepare_identity`.

    Returns:
        Joint transforms in the model hierarchy.
    """
    if identity is None:
        assert shape is not None
        batch_shape = tuple(hand_pose.shape[: -(self.num_rot_dims + 1)])
        shape = np.broadcast_to(shape, (*batch_shape, shape.shape[-1]))
        identity = self.prepare_identity(shape, skip_vertices=True)
    pose = self.prepare_pose(hand_pose, wrist_rotation, identity=identity, skip_vertices=True)
    return self._kernel.forward_skeleton(
        self.weights,
        pose["skeleton_transforms"],
        global_rotation=global_rotation,
        global_translation=global_translation,
        joint_indices=joint_indices,
        rotation_type=self.rotation_type,
    )

prepare_identity

prepare_identity(shape, skip_vertices=False)

Precompute shape-dependent state for repeated forward passes.

Source code in src/body_models/parts/mano/numpy.py

def prepare_identity(
    self,
    shape: Float[np.ndarray, "*batch 10"],
    skip_vertices: bool = False,
) -> ManoIdentity:
    """Precompute shape-dependent state for repeated forward passes."""
    return self._kernel.prepare_identity(self.weights, shape, skip_vertices=skip_vertices)

prepare_pose

prepare_pose(
    hand_pose, wrist_rotation=None, *, identity, skip_vertices=False
)

Precompute pose-dependent state for repeated forward passes.

Source code in src/body_models/parts/mano/numpy.py

def prepare_pose(
    self,
    hand_pose: Float[np.ndarray, "B 15 N"] | Float[np.ndarray, "B 15 3 3"],
    wrist_rotation: Float[np.ndarray, "B N"] | Float[np.ndarray, "B 3 3"] | None = None,
    *,
    identity: ManoIdentity,
    skip_vertices: bool = False,
) -> ManoPreparedPose:
    """Precompute pose-dependent state for repeated forward passes."""
    return self._kernel.prepare_pose(
        self.weights,
        hand_pose,
        wrist_rotation,
        rotation_type=self.rotation_type,
        local_joint_offsets=identity["local_joint_offsets"],
        rest_joints=identity["rest_joints"],
        skip_vertices=skip_vertices,
    )

joint_index

joint_index(joint)

Resolve a standard joint to this model's native joint index.

Source code in src/body_models/base.py

def joint_index(self, joint: Joint) -> int:
    """Resolve a standard joint to this model's native joint index."""
    if not isinstance(joint, Joint):
        raise TypeError("joint_index() expects a body_models.Joint; use joint_names.index(...) for native names.")
    try:
        native_name = self.common_joints[joint]
    except KeyError as exc:
        raise KeyError(f"{self.__class__.__name__} has no standard joint {joint.value!r}") from exc
    return self.joint_names.index(native_name)

get_tpose

get_tpose(batch_dims=(), **kwargs)

Get parameters for the SMPL-style T-pose.

Source code in src/body_models/base.py

def get_tpose(
    self,
    batch_dims: tuple[int, ...] = (),
    **kwargs: Any,
) -> dict[str, Any]:
    """Get parameters for the SMPL-style T-pose."""
    raise NotImplementedError("Canonical body poses are not defined for this model.")

get_apose

get_apose(batch_dims=(), **kwargs)

Get parameters for the MHR-style A-pose.

Source code in src/body_models/base.py

def get_apose(
    self,
    batch_dims: tuple[int, ...] = (),
    **kwargs: Any,
) -> dict[str, Any]:
    """Get parameters for the MHR-style A-pose."""
    raise NotImplementedError("Canonical body poses are not defined for this model.")

prepare_skinning

prepare_skinning(*, identity, pose)

Pack prepared model state into renderer-ready skinning inputs.

Source code in src/body_models/base.py

def prepare_skinning(self, *, identity: Mapping[str, Any], pose: Mapping[str, Any]) -> SkinningPayload:
    """Pack prepared model state into renderer-ready skinning inputs."""
    if self.is_rigid_body:
        raise NotImplementedError(f"{self.__class__.__name__} is rigid and does not support skinning.")

    skinning: SkinningPayload = {
        "rest_vertices": identity["rest_vertices"],
        "skinning_transforms": pose["skinning_transforms"],
        "skin_weights": self.skin_weights,
        "faces": self.faces,
    }
    if "pose_offsets" in pose:
        skinning["pose_offsets"] = pose["pose_offsets"]
    return skinning