mmcv.ops.points_in_boxes_all¶
- mmcv.ops.points_in_boxes_all(points: Tensor, boxes: Tensor) Tensor[source]¶
Find all boxes in which each point is (CUDA/MUSA).
- Parameters:
points (torch.Tensor) – [B, M, 3], [x, y, z] in LiDAR/DEPTH coordinate
boxes (torch.Tensor) – [B, T, 7], num_valid_boxes <= T, [x, y, z, x_size, y_size, z_size, rz], (x, y, z) is the bottom center.
- Returns:
Return the box indices of points with the shape of (B, M, T). Default background = 0.
- Return type: