Hugging Face's logo

Spaces:
oguzakif
/
video-object-remover
Running on T4

App Files Community
1
video-object-remover
File size: 5,227 Bytes 
d4b77ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
 
import torch
import torch.nn as nn
import torch.nn.functional as F


class FlowHead(nn.Module):
    def __init__(self, input_dim=128, hidden_dim=256):
        super(FlowHead, self).__init__()
        self.conv1 = nn.Conv2d(input_dim, hidden_dim, 3, padding=1)
        self.conv2 = nn.Conv2d(hidden_dim, 2, 3, padding=1)
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        return self.conv2(self.relu(self.conv1(x)))

class ConvGRU(nn.Module):
    def __init__(self, hidden_dim=128, input_dim=192+128):
        super(ConvGRU, self).__init__()
        self.convz = nn.Conv2d(hidden_dim+input_dim, hidden_dim, 3, padding=1)
        self.convr = nn.Conv2d(hidden_dim+input_dim, hidden_dim, 3, padding=1)
        self.convq = nn.Conv2d(hidden_dim+input_dim, hidden_dim, 3, padding=1)

    def forward(self, h, x):
        hx = torch.cat([h, x], dim=1)

        z = torch.sigmoid(self.convz(hx))
        r = torch.sigmoid(self.convr(hx))
        q = torch.tanh(self.convq(torch.cat([r*h, x], dim=1)))

        h = (1-z) * h + z * q
        return h

class SepConvGRU(nn.Module):
    def __init__(self, hidden_dim=128, input_dim=192+128):
        super(SepConvGRU, self).__init__()
        self.convz1 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (1,5), padding=(0,2))
        self.convr1 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (1,5), padding=(0,2))
        self.convq1 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (1,5), padding=(0,2))

        self.convz2 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (5,1), padding=(2,0))
        self.convr2 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (5,1), padding=(2,0))
        self.convq2 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (5,1), padding=(2,0))


    def forward(self, h, x):
        # horizontal
        hx = torch.cat([h, x], dim=1)
        z = torch.sigmoid(self.convz1(hx))
        r = torch.sigmoid(self.convr1(hx))
        q = torch.tanh(self.convq1(torch.cat([r*h, x], dim=1)))        
        h = (1-z) * h + z * q

        # vertical
        hx = torch.cat([h, x], dim=1)
        z = torch.sigmoid(self.convz2(hx))
        r = torch.sigmoid(self.convr2(hx))
        q = torch.tanh(self.convq2(torch.cat([r*h, x], dim=1)))       
        h = (1-z) * h + z * q

        return h

class SmallMotionEncoder(nn.Module):
    def __init__(self, args):
        super(SmallMotionEncoder, self).__init__()
        cor_planes = args.corr_levels * (2*args.corr_radius + 1)**2
        self.convc1 = nn.Conv2d(cor_planes, 96, 1, padding=0)
        self.convf1 = nn.Conv2d(2, 64, 7, padding=3)
        self.convf2 = nn.Conv2d(64, 32, 3, padding=1)
        self.conv = nn.Conv2d(128, 80, 3, padding=1)

    def forward(self, flow, corr):
        cor = F.relu(self.convc1(corr))
        flo = F.relu(self.convf1(flow))
        flo = F.relu(self.convf2(flo))
        cor_flo = torch.cat([cor, flo], dim=1)
        out = F.relu(self.conv(cor_flo))
        return torch.cat([out, flow], dim=1)

class BasicMotionEncoder(nn.Module):
    def __init__(self, args):
        super(BasicMotionEncoder, self).__init__()
        cor_planes = args.corr_levels * (2*args.corr_radius + 1)**2
        self.convc1 = nn.Conv2d(cor_planes, 256, 1, padding=0)
        self.convc2 = nn.Conv2d(256, 192, 3, padding=1)
        self.convf1 = nn.Conv2d(2, 128, 7, padding=3)
        self.convf2 = nn.Conv2d(128, 64, 3, padding=1)
        self.conv = nn.Conv2d(64+192, 128-2, 3, padding=1)

    def forward(self, flow, corr):
        cor = F.relu(self.convc1(corr))
        cor = F.relu(self.convc2(cor))
        flo = F.relu(self.convf1(flow))
        flo = F.relu(self.convf2(flo))

        cor_flo = torch.cat([cor, flo], dim=1)
        out = F.relu(self.conv(cor_flo))
        return torch.cat([out, flow], dim=1)

class SmallUpdateBlock(nn.Module):
    def __init__(self, args, hidden_dim=96):
        super(SmallUpdateBlock, self).__init__()
        self.encoder = SmallMotionEncoder(args)
        self.gru = ConvGRU(hidden_dim=hidden_dim, input_dim=82+64)
        self.flow_head = FlowHead(hidden_dim, hidden_dim=128)

    def forward(self, net, inp, corr, flow):
        motion_features = self.encoder(flow, corr)
        inp = torch.cat([inp, motion_features], dim=1)
        net = self.gru(net, inp)
        delta_flow = self.flow_head(net)

        return net, None, delta_flow

class BasicUpdateBlock(nn.Module):
    def __init__(self, args, hidden_dim=128, input_dim=128):
        super(BasicUpdateBlock, self).__init__()
        self.args = args
        self.encoder = BasicMotionEncoder(args)
        self.gru = SepConvGRU(hidden_dim=hidden_dim, input_dim=128+hidden_dim)
        self.flow_head = FlowHead(hidden_dim, hidden_dim=256)

        self.mask = nn.Sequential(
            nn.Conv2d(128, 256, 3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 64*9, 1, padding=0))

    def forward(self, net, inp, corr, flow, upsample=True):
        motion_features = self.encoder(flow, corr)
        inp = torch.cat([inp, motion_features], dim=1)

        net = self.gru(net, inp)
        delta_flow = self.flow_head(net)

        # scale mask to balence gradients
        mask = .25 * self.mask(net)
        return net, mask, delta_flow