def forward(ctx, xyz, npoint):
"""
Uses iterative furthest point sampling to select a set of npoint features that have the largest
minimum distance
:param ctx:
:param xyz: (B, N, 3) where N > npoint
:param npoint: int, number of features in the sampled set
:return:
output: (B, npoint) tensor containing the set
"""
return _ext.furthest_point_sampling(xyz, npoint)
def forward(ctx, xyz: torch.Tensor, npoint: int) -> torch.Tensor:
r"""
Uses iterative furthest point sampling to select a set of npoint features that have the largest
minimum distance
Parameters
----------
xyz : torch.Tensor
(B, N, 3) tensor where N > npoint
npoint : int32
number of features in the sampled set
Returns
-------
torch.Tensor
(B, npoint) tensor containing the set
"""
return _ext.furthest_point_sampling(xyz, npoint)
def forward(ctx, xyz, npoint):
# type: (Any, torch.Tensor, int) -> torch.Tensor
r"""
Uses iterative furthest point sampling to select a set of npoint features that have the largest
minimum distance
Parameters
----------
xyz : torch.Tensor
(B, N, 3) tensor where N > npoint
npoint : int32
number of features in the sampled set
Returns
-------
torch.Tensor
(B, npoint) tensor containing the set
"""
fps_inds = _ext.furthest_point_sampling(xyz, npoint)
ctx.mark_non_differentiable(fps_inds)
return fps_inds
def farthest_pts_sampling_tensor(pts, num_samples, return_sampled_idx=False):
'''
:param pts: bn, n, 3
:param num_samples:
:return:
'''
sampled_pts_idx = _ext.furthest_point_sampling(pts, num_samples)
sampled_pts_idx_viewed = sampled_pts_idx.view(
sampled_pts_idx.shape[0] * sampled_pts_idx.shape[1]).cuda().type(
torch.LongTensor)
batch_idxs = torch.tensor(range(pts.shape[0])).type(torch.LongTensor)
batch_idxs_viewed = batch_idxs[:, None].repeat(
1, sampled_pts_idx.shape[1]).view(batch_idxs.shape[0] *
sampled_pts_idx.shape[1])
sampled_pts = pts[batch_idxs_viewed, sampled_pts_idx_viewed, :]
sampled_pts = sampled_pts.view(pts.shape[0], num_samples, 3)
if return_sampled_idx == False:
return sampled_pts
else:
return sampled_pts, sampled_pts_idx
