File size: 1,899 Bytes
587665f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
import torch
import torch.nn.functional as F
from .utils import bilinear_sampler, coords_grid
class CorrBlock:
def __init__(self, fmap1, fmap2, num_levels=4, radius=4):
self.num_levels = num_levels
self.radius = radius
self.corr_pyramid = []
# all pairs correlation
corr = CorrBlock.corr(fmap1, fmap2)
batch, h1, w1, dim, h2, w2 = corr.shape
corr = corr.reshape(batch*h1*w1, dim, h2, w2)
self.corr_pyramid.append(corr)
for i in range(self.num_levels-1):
corr = F.avg_pool2d(corr, 2, stride=2)
self.corr_pyramid.append(corr)
def __call__(self, coords):
r = self.radius
coords = coords.permute(0, 2, 3, 1)
batch, h1, w1, _ = coords.shape
out_pyramid = []
for i in range(self.num_levels):
corr = self.corr_pyramid[i]
dx = torch.linspace(-r, r, 2*r+1)
dy = torch.linspace(-r, r, 2*r+1)
delta = torch.stack(torch.meshgrid(dy, dx), dim=-1).to(coords.device)
centroid_lvl = coords.reshape(batch*h1*w1, 1, 1, 2) / 2**i
delta_lvl = delta.view(1, 2*r+1, 2*r+1, 2)
coords_lvl = centroid_lvl + delta_lvl
corr = bilinear_sampler(corr, coords_lvl)
corr = corr.view(batch, h1, w1, -1)
out_pyramid.append(corr)
out = torch.cat(out_pyramid, dim=-1)
return out.permute(0, 3, 1, 2).contiguous().float()
@staticmethod
def corr(fmap1, fmap2):
batch, dim, ht, wd = fmap1.shape
fmap1 = fmap1.view(batch, dim, ht*wd)
fmap2 = fmap2.view(batch, dim, ht*wd)
corr = torch.matmul(fmap1.transpose(1,2), fmap2)
corr = corr.view(batch, ht, wd, 1, ht, wd)
return corr / torch.sqrt(torch.tensor(dim).float())
|