1 vin.geometry.pose_batch

vin.geometry.pose_batch

Pose-batch shape helpers for VIN candidate scorers.

VIN scorer inputs use :class:efm3d.aria.pose.PoseTW tensors with explicit candidate and batch axes. These helpers centralize the tolerated shorthand forms before model code computes relative poses, projection grids, or rollout candidate scores.

1.1 Functions

Name	Description
ensure_candidate_batch	Ensure candidate camera poses are shaped as PoseTW["B N 12"].
ensure_pose_batch	Broadcast one pose tensor to the VIN batch size.

1.1.1 ensure_candidate_batch

vin.geometry.pose_batch.ensure_candidate_batch(candidate_poses_world_cam)

Ensure candidate camera poses are shaped as PoseTW["B N 12"].

1.1.1.1 Parameters

Name	Type	Description	Default
candidate_poses_world_cam	PoseBatchT	Candidate camera poses T_w_c with shape PoseTW["N 12"] for one snippet or PoseTW["B N 12"] for a batch.	required

1.1.1.2 Returns

Name	Type	Description
	PoseBatchT	Candidate poses with an explicit batch axis.

1.1.1.3 Raises

Name	Type	Description
	ValueError	If the pose tensor is neither (N, 12) nor (B, N, 12).

1.1.2 ensure_pose_batch

vin.geometry.pose_batch.ensure_pose_batch(pose, *, batch_size, name)

Broadcast one pose tensor to the VIN batch size.

1.1.2.1 Parameters

Name	Type	Description	Default
pose	PoseBatchT	Pose tensor with shape PoseTW["12"], PoseTW["1 12"], or PoseTW["B 12"].	required
batch_size	int	Required batch size B.	required
name	str	Human-readable input name used in validation errors.	required

1.1.2.2 Returns

Name	Type	Description
	PoseBatchT	pose shaped as PoseTW["B 12"].

1.1.2.3 Raises

Name	Type	Description
	ValueError	If pose has an unsupported rank or a non-broadcastable batch dimension.