SMPL-H

SMPL-H extends SMPL with articulated MANO hands.

Setup

SMPL-H requires registration at mano.is.tue.mpg.de.

body-models download smplh

Or configure files by gender:

body-models set smplh-neutral /path/to/smplh/neutral/model.npz
body-models set smplh-male /path/to/smplh/male/model.npz
body-models set smplh-female /path/to/smplh/female/model.npz

The downloader uses the "Extended SMPL+H model (used in AMASS project)" archive.

API

body_models.smplh.numpy.SMPLH

SMPLH(
    *,
    model_path=None,
    gender=None,
    flat_hand_mean=False,
    rotation_type="axis_angle",
    simplify=1.0,
)

Bases: body_models.smplh._model.SMPLH

Skinned human body model with articulated hands.

METHOD	DESCRIPTION
apply_pose_correctives	Apply prepared pose correctives to identity-dependent rest vertices.
forward_points	Compute positions defined by a prepared vertex mapping.
forward_skeleton	Compute posed joint transforms.
forward_vertices	Compute posed mesh vertices.
get_rest_pose	Return zero identity controls and identity rotations.
joint_index	Resolve a common joint to this model's native joint index.
prepare_point_regressor	Preproject a vertex mapping and the model's linear identity bases.
get_apose	Return the SMPL-H A-pose.
get_tpose	Return the SMPL-H T-pose.
prepare_identity	Precompute shape-dependent state for repeated forward passes.
prepare_pose	Precompute pose-dependent state for repeated forward passes.

ATTRIBUTE	DESCRIPTION
common_joints	Common anatomical joints mapped to this model's native joint names.
has_face	bool(x) -> bool
has_hands	bool(x) -> bool
num_joints	Number of joints in the skeleton.
pose_joint_indices	Canonical joints whose local transforms are driven by each pose parameter.
runtime	Array runtime used by this model.
skinning_spec	Static topology, render-rig weights, and optional pose correctives.
symmetric_joints	Left/right joint pairs as (left_index, right_index), in joint order.
NUM_EXPR_COEFFS	int([x]) -> integer
NUM_BODY_CONTROLS	int([x]) -> integer
NUM_HAND_CONTROLS	int([x]) -> integer
NUM_JOINTS	int([x]) -> integer
NUM_SHAPE_COEFFS	int([x]) -> integer

common_joints property

common_joints

Common anatomical joints mapped to this model's native joint names.

has_face class-attribute

has_face = False

bool(x) -> bool

Returns True when the argument x is true, False otherwise. The builtins True and False are the only two instances of the class bool. The class bool is a subclass of the class int, and cannot be subclassed.

has_hands class-attribute

has_hands = True

bool(x) -> bool

Returns True when the argument x is true, False otherwise. The builtins True and False are the only two instances of the class bool. The class bool is a subclass of the class int, and cannot be subclassed.

num_joints property

num_joints

Number of joints in the skeleton.

pose_joint_indices property

pose_joint_indices

Canonical joints whose local transforms are driven by each pose parameter.

runtime property

runtime

Array runtime used by this model.

skinning_spec property

skinning_spec

Static topology, render-rig weights, and optional pose correctives.

symmetric_joints property

symmetric_joints

Left/right joint pairs as (left_index, right_index), in joint order.

Indices address the J axis of :meth:forward_skeleton outputs and cover the whole native skeleton, including joints outside the :class:Joint vocabulary. Unpaired joints lie on the midline. Pairs describe index correspondence only, not how to mirror a pose.

RAISES	DESCRIPTION
ValueError	If a sided joint name has no counterpart.

NUM_EXPR_COEFFS class-attribute

NUM_EXPR_COEFFS = 0

int([x]) -> integer int(x, base=10) -> integer

Convert a number or string to an integer, or return 0 if no arguments are given. If x is a number, return x.int(). For floating point numbers, this truncates towards zero.

If x is not a number or if base is given, then x must be a string, bytes, or bytearray instance representing an integer literal in the given base. The literal can be preceded by '+' or '-' and be surrounded by whitespace. The base defaults to 10. Valid bases are 0 and 2-36. Base 0 means to interpret the base from the string as an integer literal.

int('0b100', base=0) 4

NUM_BODY_CONTROLS class-attribute

NUM_BODY_CONTROLS = 21

int([x]) -> integer int(x, base=10) -> integer

Convert a number or string to an integer, or return 0 if no arguments are given. If x is a number, return x.int(). For floating point numbers, this truncates towards zero.

If x is not a number or if base is given, then x must be a string, bytes, or bytearray instance representing an integer literal in the given base. The literal can be preceded by '+' or '-' and be surrounded by whitespace. The base defaults to 10. Valid bases are 0 and 2-36. Base 0 means to interpret the base from the string as an integer literal.

int('0b100', base=0) 4

NUM_HAND_CONTROLS class-attribute

NUM_HAND_CONTROLS = 30

int([x]) -> integer int(x, base=10) -> integer

Convert a number or string to an integer, or return 0 if no arguments are given. If x is a number, return x.int(). For floating point numbers, this truncates towards zero.

If x is not a number or if base is given, then x must be a string, bytes, or bytearray instance representing an integer literal in the given base. The literal can be preceded by '+' or '-' and be surrounded by whitespace. The base defaults to 10. Valid bases are 0 and 2-36. Base 0 means to interpret the base from the string as an integer literal.

int('0b100', base=0) 4

NUM_JOINTS class-attribute

NUM_JOINTS = 52

int([x]) -> integer int(x, base=10) -> integer

Convert a number or string to an integer, or return 0 if no arguments are given. If x is a number, return x.int(). For floating point numbers, this truncates towards zero.

If x is not a number or if base is given, then x must be a string, bytes, or bytearray instance representing an integer literal in the given base. The literal can be preceded by '+' or '-' and be surrounded by whitespace. The base defaults to 10. Valid bases are 0 and 2-36. Base 0 means to interpret the base from the string as an integer literal.

int('0b100', base=0) 4

NUM_SHAPE_COEFFS class-attribute

NUM_SHAPE_COEFFS = 16

int([x]) -> integer int(x, base=10) -> integer

Convert a number or string to an integer, or return 0 if no arguments are given. If x is a number, return x.int(). For floating point numbers, this truncates towards zero.

If x is not a number or if base is given, then x must be a string, bytes, or bytearray instance representing an integer literal in the given base. The literal can be preceded by '+' or '-' and be surrounded by whitespace. The base defaults to 10. Valid bases are 0 and 2-36. Base 0 means to interpret the base from the string as an integer literal.

int('0b100', base=0) 4

apply_pose_correctives

apply_pose_correctives(*, identity, pose)

Apply prepared pose correctives to identity-dependent rest vertices.

Source code in src/body_models/_base.py

def apply_pose_correctives(
    self,
    *,
    identity: SkinningIdentity,
    pose: SkinningPose,
) -> Float[Array, "*batch V 3"]:
    """Apply prepared pose correctives to identity-dependent rest vertices."""
    vertices = identity["rest_vertices"]
    coefficients = pose.get("pose_coefficients")
    if coefficients is None:
        return vertices
    basis = self._corrective_basis
    if basis is None:
        raise RuntimeError("Prepared pose has corrective coefficients, but the model has no corrective basis.")
    return vertices + basis.apply(coefficients)

forward_points

forward_points(
    body_pose,
    hand_pose,
    *,
    point_regressor,
    pelvis_rotation=None,
    shape=None,
    identity=None,
    global_rotation=None,
    global_translation=None,
)

Compute positions defined by a prepared vertex mapping.

Source code in src/body_models/smplh/_model.py

def forward_points(
    self,
    body_pose: Float[Array, "*batch 21 N"] | Float[Array, "*batch 21 3 3"],
    hand_pose: Float[Array, "*batch 30 N"] | Float[Array, "*batch 30 3 3"],
    *,
    point_regressor: PointRegressor,
    pelvis_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    shape: Float[Array, "*batch S"] | None = None,
    identity: LinearIdentity | None = None,
    global_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    global_translation: Float[Array, "*batch 3"] | None = None,
) -> Float[Array, "*batch K 3"]:
    """Compute positions defined by a prepared vertex mapping."""
    self._validate_identity_arguments(identity, shape=shape)
    if identity is not None:
        pose = self.prepare_pose(
            body_pose,
            hand_pose,
            pelvis_rotation=pelvis_rotation,
            identity=identity,
        )
        return self._deform_points(point_regressor, identity, pose, global_rotation, global_translation)

    batch_shape = body_pose.shape[: -(self._num_rot_dims + 1)]
    resolved = self._resolve_identity_coefficients(batch_shape, shape=shape)
    skeleton_identity = self._prepare_skeleton_identity(*resolved)
    pose = self.prepare_pose(
        body_pose,
        hand_pose,
        pelvis_rotation=pelvis_rotation,
        identity=skeleton_identity,
    )
    return self._deform_linear_points(
        point_regressor,
        resolved,
        pose,
        global_rotation,
        global_translation,
    )

forward_skeleton

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

Compute posed joint transforms.

Source code in src/body_models/smplh/_model.py

def forward_skeleton(
    self,
    body_pose: Float[Array, "*batch 21 N"] | Float[Array, "*batch 21 3 3"],
    hand_pose: Float[Array, "*batch 30 N"] | Float[Array, "*batch 30 3 3"],
    *,
    pelvis_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    shape: Float[Array, "*batch S"] | None = None,
    identity: LinearIdentity | None = None,
    global_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    global_translation: Float[Array, "*batch 3"] | None = None,
    joint_indices: Sequence[int] | None = None,
) -> Float[Array, "*batch 52 4 4"]:
    """Compute posed joint transforms."""
    self._validate_identity_arguments(identity, shape=shape)
    if identity is None:
        batch_shape = body_pose.shape[: -(self._num_rot_dims + 1)]
        resolved = self._resolve_identity_coefficients(batch_shape, shape=shape)
        skeleton_identity = self._prepare_skeleton_identity(*resolved)
    else:
        skeleton_identity = identity

    skeleton = core.prepare_skeleton(
        self._runtime,
        self._assets.kinematic_tree,
        self._assets.hand_mean,
        body_pose,
        hand_pose,
        pelvis_rotation,
        self.rotation_type,
        local_joint_offsets=skeleton_identity["local_joint_offsets"],
        joint_indices=joint_indices,
    )
    return self._transform_skeleton(
        skeleton,
        global_rotation,
        global_translation,
    )

forward_vertices

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

Compute posed mesh vertices.

Source code in src/body_models/smplh/_model.py

def forward_vertices(
    self,
    body_pose: Float[Array, "*batch 21 N"] | Float[Array, "*batch 21 3 3"],
    hand_pose: Float[Array, "*batch 30 N"] | Float[Array, "*batch 30 3 3"],
    *,
    pelvis_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    shape: Float[Array, "*batch S"] | None = None,
    identity: LinearIdentity | None = None,
    global_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    global_translation: Float[Array, "*batch 3"] | None = None,
    vertex_indices: Sequence[int] | None = None,
) -> Float[Array, "*batch V 3"]:
    """Compute posed mesh vertices."""
    self._validate_identity_arguments(identity, shape=shape)
    if identity is None:
        batch_shape = body_pose.shape[: -(self._num_rot_dims + 1)]
        identity = self.prepare_identity(*self._resolve_identity_coefficients(batch_shape, shape=shape))

    pose = self.prepare_pose(body_pose, hand_pose, pelvis_rotation=pelvis_rotation, identity=identity)
    return self._deform_vertices(
        identity,
        pose,
        global_rotation,
        global_translation,
        vertex_indices,
    )

get_rest_pose

get_rest_pose(*, batch_dims=(), dtype=None, hands='default')

Return zero identity controls and identity rotations.

Source code in src/body_models/smplh/_model.py

def get_rest_pose(
    self,
    *,
    batch_dims: tuple[int, ...] = (),
    dtype: Any | None = None,
    hands: HandPreset = "default",
) -> dict[str, Float[Array, "..."]]:
    """Return zero identity controls and identity rotations."""
    if hands not in ("default", "flat", "rest"):
        raise ValueError(f"Invalid hands: {hands!r}")

    params = super().get_rest_pose(batch_dims=batch_dims, dtype=dtype)
    if hands != "default":
        params["hand_pose"] = self._hand_preset(batch_dims, params["hand_pose"], hands)
    return params

joint_index

joint_index(joint)

Resolve a common 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 common 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 common joint {joint.value!r}") from exc
    return self.joint_names.index(native_name)

prepare_point_regressor

prepare_point_regressor(mapping)

Preproject a vertex mapping and the model's linear identity bases.

Source code in src/body_models/_linear_blendshape.py

def prepare_point_regressor(
    self,
    mapping: Float[Array, "K V"],
) -> PointRegressor:
    """Preproject a vertex mapping and the model's linear identity bases."""
    regressor = super().prepare_point_regressor(mapping)
    xp = self._runtime.xp
    regressor["template"] = point_regression.project_vertex_values(
        regressor,
        self.rest_vertices,
        xp=xp,
    )
    regressor["identity_bases"] = tuple(
        point_regression.project_vertex_values(regressor, basis, xp=xp) for basis in self._point_identity_bases
    )
    return regressor

get_apose

get_apose(*, batch_dims=(), dtype=None, hands='default')

Return the SMPL-H A-pose.

Source code in src/body_models/smplh/_model.py

def get_apose(
    self,
    *,
    batch_dims: tuple[int, ...] = (),
    dtype: Any | None = None,
    hands: HandPreset = "default",
) -> dict[str, Float[Array, "..."]]:
    """Return the SMPL-H A-pose."""
    params = self.get_rest_pose(batch_dims=batch_dims, dtype=dtype, hands=hands)
    axis_angle = self._runtime.asarray(SMPLH_BODY_PRESETS["a_pose"], like=params["body_pose"])
    axis_angle = self._runtime.xp.broadcast_to(axis_angle, (*batch_dims, *axis_angle.shape))
    params["body_pose"] = SO3.convert(
        axis_angle,
        src="axis_angle",
        dst=self.rotation_type,
        xp=self._runtime.xp,
    )
    return params

get_tpose

get_tpose(*, batch_dims=(), dtype=None, hands='default')

Return the SMPL-H T-pose.

Source code in src/body_models/smplh/_model.py

def get_tpose(
    self,
    *,
    batch_dims: tuple[int, ...] = (),
    dtype: Any | None = None,
    hands: HandPreset = "default",
) -> dict[str, Float[Array, "..."]]:
    """Return the SMPL-H T-pose."""
    return self.get_rest_pose(batch_dims=batch_dims, dtype=dtype, hands=hands)

prepare_identity

prepare_identity(shape)

Precompute shape-dependent state for repeated forward passes.

Source code in src/body_models/smplh/_model.py

def prepare_identity(
    self,
    shape: Float[Array, "*batch S"],
) -> LinearIdentity:
    """Precompute shape-dependent state for repeated forward passes."""
    return core.prepare_identity(
        xp=self._runtime.xp,
        v_template=self._assets.v_template,
        shapedirs=self._assets.shapedirs,
        j_template=self._assets.j_template,
        j_shapedirs=self._assets.j_shapedirs,
        parents=self._assets.kinematic_tree.parents,
        shape=shape,
    )

prepare_pose

prepare_pose(body_pose, hand_pose, *, pelvis_rotation=None, identity)

Precompute pose-dependent state for repeated forward passes.

Source code in src/body_models/smplh/_model.py

def prepare_pose(
    self,
    body_pose: Float[Array, "*batch 21 N"] | Float[Array, "*batch 21 3 3"],
    hand_pose: Float[Array, "*batch 30 N"] | Float[Array, "*batch 30 3 3"],
    *,
    pelvis_rotation: Float[Array, "*batch N"] | Float[Array, "*batch 3 3"] | None = None,
    identity: core.SmplhSkeletonIdentity,
) -> SkinningPose:
    """Precompute pose-dependent state for repeated forward passes."""
    return core.prepare_pose(
        self._runtime,
        self._assets.kinematic_tree,
        hand_mean=self._assets.hand_mean,
        body_pose=body_pose,
        hand_pose=hand_pose,
        pelvis_rotation=pelvis_rotation,
        rotation_type=self.rotation_type,
        local_joint_offsets=identity["local_joint_offsets"],
        rest_joints=identity["rest_joints"],
    )