1 CandidatePointClouds

rendering.candidate_pointclouds.CandidatePointClouds(
    points,
    lengths,
    semidense_points,
    semidense_length,
    occupancy_bounds,
)

Batched candidate point clouds plus fused semi-dense reconstruction.

1.1 Attributes

Name	Description
points	Tensor[‘B’, ‘P’, 3] padded candidate point clouds (world frame).
lengths	Tensor[‘B’] actual point counts per candidate.
semidense_points	Tensor[‘K’, 3] collapsed semi-dense SLAM point cloud.
semidense_length	Tensor[1] number of valid semi-dense points.
occupancy_bounds	Tensor[6] = [xmin, xmax, ymin, ymax, zmin, zmax] covering snippet + candidates.

1.2 Methods

Name	Description
to_serializable	Serialize this point-cloud batch into a cache-friendly CPU payload.
from_serializable	Reconstruct one point-cloud batch from a serialized payload.

1.2.1 to_serializable

rendering.candidate_pointclouds.CandidatePointClouds.to_serializable()

Serialize this point-cloud batch into a cache-friendly CPU payload.

1.2.2 from_serializable

rendering.candidate_pointclouds.CandidatePointClouds.from_serializable(
    payload,
    *,
    device,
)

Reconstruct one point-cloud batch from a serialized payload.

1.2.2.1 Parameters

Name	Type	Description	Default
payload	dict[str, object]	Serialized payload produced by to_serializable.	required
device	torch.device	Destination device for tensors.	required

1.2.2.2 Returns

Name	Type	Description
	'CandidatePointClouds'	Reconstructed candidate-pointcloud batch.