open3d.ml.tf.ops.trilinear_devoxelize_grad#

open3d.ml.tf.ops.trilinear_devoxelize_grad(grad_y, indices, weights, resolution, name=None)#

Gradient function for Trilinear Devoxelize op.

This function takes feature gradients and indices, weights returned from the op and computes gradient for voxelgrid.

Parameters:

  • grad_y – A Tensor of type float32. Gradients for the interpolated features. Shape is [B, C, N].

  • indices – A Tensor of type int32. Indices which are used to interpolate features. Shape is [B, 8, N].

  • weights – A Tensor of type float32. Weights for each index used to interpolate features. Shape is [B, 8, N].

  • resolution – An int. Integer attribute defining resolution of the grid.

  • name – A name for the operation (optional).

Returns:

A Tensor of type float32. Output gradients for the voxel grid. Shape is [B, C, R, R, R]