1 vin.feature_bank.pooling

vin.feature_bank.pooling

Pooling helpers for actor-visible point descriptors.

This module provides frame-axis weighted means and masked point-set reductions. The latter use only commutative reductions, so reordering selected point rows does not change their outputs.

1.1 Functions

Name Description
pool_multiview_point_features Pool per-frame point descriptors with projection-valid weights.
pool_point_query Compute permutation-invariant masked point-pool summaries.

1.1.1 pool_multiview_point_features

vin.feature_bank.pooling.pool_multiview_point_features(
    sampled_features,
    valid_mask,
    *,
    point_weights=None,
    eps=1e-06,
)

Pool per-frame point descriptors with projection-valid weights.

1.1.1.1 Parameters

Name Type Description Default
sampled_features Tensor Tensor["B T N C"] sampled logged-frame features. required
valid_mask Tensor Tensor["B T N", bool] projection-valid samples. required
point_weights Tensor | None Optional weights shaped N, T, B N, B T, T N, or B T N. Typical values encode point uncertainty, support, recency, or logged-view quality. None
eps float Positive denominator guard. 1e-06

1.1.1.2 Returns

Name Type Description
FeaturePoolingResult Weighted means and validity diagnostics.

1.1.2 pool_point_query

vin.feature_bank.pooling.pool_point_query(
    point_features,
    point_mask,
    *,
    eps=1e-06,
)

Compute permutation-invariant masked point-pool summaries.

Mean, maximum, population standard deviation, and count are symmetric in the N_p axis. Jointly permuting point_features and point_mask therefore leaves every output unchanged. This is set-permutation invariance, not a graph-isomorphism contract; no edges or message passing are constructed here.

1.1.2.1 Parameters

Name Type Description Default
point_features Tensor Tensor["B N_p C", float32] point descriptors. required
point_mask Tensor Tensor["B N_p", bool] points included in the query. required
eps float Positive denominator guard for mean and std. 1e-06

1.1.2.2 Returns

Name Type Description
PointQueryPool Mean, max, std, count, and empty-support mask.
Back to top