# open3d.ml.torch.ops¶

Functional API with operators.

These are the building blocks for the layers. See The layer API for an easy to use high level interface.

Functions

 build_spatial_hash_table(points, radius, …) Creates a spatial hash table meant as input for fixed_radius_search continuous_conv(filters, out_positions, …) Continuous convolution of two pointclouds. continuous_conv_transpose(filters, …[, …]) Continuous tranpose convolution of two pointclouds. fixed_radius_search(points, queries, radius, …) Computes the indices of all neighbors within a radius. invert_neighbors_list(num_points, …) Inverts a neighbors list made of neighbors_index and neighbors_row_splits. knn_search(points, queries, k, …[, …]) Computes the indices of k nearest neighbors. nms(boxes, scores, nms_overlap_thresh) Performs non-maximum suppression of bounding boxes. radius_search(points, queries, radii, …[, …]) Computes the indices and distances of all neighbours within a radius. reduce_subarrays_sum(values, row_splits) Computes the sum for each subarray in a flat vector of arrays. voxel_pooling(positions, features, voxel_size) Spatial pooling for point clouds by combining points that fall into the same voxel bin. voxelize(points, row_splits, voxel_size, …) Voxelization for point clouds.