Uses iterative furthest point sampling to select a set of npoint features that have the largest minimum distance to the sampled point set :param coords: coordinates of points, FloatTensor[B, 3, N] :param num_samples: int, M :return: centers_coords: coordinates of sampled
(coords, num_samples)
| 35 | |
| 36 | |
| 37 | def furthest_point_sample(coords, num_samples): |
| 38 | """ |
| 39 | Uses iterative furthest point sampling to select a set of npoint features that have the largest |
| 40 | minimum distance to the sampled point set |
| 41 | :param coords: coordinates of points, FloatTensor[B, 3, N] |
| 42 | :param num_samples: int, M |
| 43 | :return: |
| 44 | centers_coords: coordinates of sampled centers, FloatTensor[B, 3, M] |
| 45 | """ |
| 46 | coords = coords.contiguous() |
| 47 | indices = _backend.furthest_point_sampling(coords, num_samples) |
| 48 | return gather(coords, indices) |
| 49 | |
| 50 | |
| 51 | def logits_mask(coords, logits, num_points_per_object): |
nothing calls this directly
no outgoing calls
no test coverage detected