pytorch3d.implicitron.models.renderer.sdf_renderer

sdf_renderer

class pytorch3d.implicitron.models.renderer.sdf_renderer.SignedDistanceFunctionRenderer(*args, **kwargs)[source]

Bases: BaseRenderer, Module

render_features_dimensions: int = 3
object_bounding_sphere: float = 1.0
ray_tracer: RayTracing
ray_normal_coloring_network_args: DictConfig = Field(name=None,type=None,default=<dataclasses._MISSING_TYPE object>,default_factory=<function get_default_args_field.<locals>.create>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object>,_field_type=None)
bg_color: Tuple[float, ...] = (0.0,)
soft_mask_alpha: float = 50.0
classmethod ray_tracer_tweak_args(type, args: DictConfig) → None[source]
create_ray_tracer() → None[source]
requires_object_mask() → bool[source]
forward(ray_bundle: ImplicitronRayBundle, implicit_functions: List[ImplicitFunctionWrapper], evaluation_mode: EvaluationMode = EvaluationMode.EVALUATION, object_mask: Tensor | None = None, **kwargs) → RendererOutput[source]
Parameters:

  • ray_bundle – A ImplicitronRayBundle object containing the parametrizations of the sampled rendering rays.

  • implicit_functions – single element list of ImplicitFunctionWrappers which defines the implicit function to be used.

  • evaluation_mode – one of EvaluationMode.TRAINING or EvaluationMode.EVALUATION which determines the settings used for rendering.

  • kwargs –

    object_mask: BoolTensor, denoting the silhouette of the object.

    This is a required keyword argument for SignedDistanceFunctionRenderer

Returns:

instance of RendererOutput