Skip to content

PointConv

PointConv message-passing convolutions, with and without density reweighting.

Classes:

  • PointConv –

    PointConv message passing: a per-edge feature outer-producted with a learned continuous weight.

  • PointConvDensity –

    PointConv with inverse density reweighting.

PointConv

PointConv(
    local_nn: Module,
    weight_nn: Module,
    add_self_loops: bool = False,
    eps: float = 1e-06,
    **kwargs: Unpack[MessagePassingParams],
)

Bases: MessagePassing

PointConv message passing: a per-edge feature outer-producted with a learned continuous weight.

local_nn embeds the relative position concatenated with the neighbor feature, weight_nn turns the relative position alone into the convolution weights, and their outer product is summed over the neighbors of each point.

Parameters:

  • local_nn (Module) –

    Network embedding the relative positions and neighbor features.

  • weight_nn (Module) –

    Network mapping a relative position to the convolution weights.

  • add_self_loops (bool, default: False ) –

    Whether to add a self loop to every point before propagating.

  • eps (float, default: 1e-06 ) –

    Numerical stability constant.

  • **kwargs (Unpack[MessagePassingParams], default: {} ) –

    Extra arguments for MessagePassing.

PointConvDensity

PointConvDensity(
    local_nn: Module,
    weight_nn: Module,
    density_nn: Module,
    add_self_loops: bool = False,
    eps: float = 1e-06,
    **kwargs: Unpack[MessagePassingParams],
)

Bases: MessagePassing

PointConv with inverse density reweighting.

Each neighbor's embedded feature is scaled by density_nn applied to its density relative to the densest neighbor, so that densely sampled regions do not dominate the sum.

Parameters:

  • local_nn (Module) –

    Network embedding the relative positions and neighbor features.

  • weight_nn (Module) –

    Network mapping a relative position to the convolution weights.

  • density_nn (Module) –

    Network mapping a relative density to a per-edge scale.

  • add_self_loops (bool, default: False ) –

    Whether to add a self loop to every point before propagating.

  • eps (float, default: 1e-06 ) –

    Numerical stability constant.

  • **kwargs (Unpack[MessagePassingParams], default: {} ) –

    Extra arguments for MessagePassing.