标签:recovery 部分 2018年 视角 layer 恢复 and str res
从单张图像中恢复 2D keypoints + 3D keypoints + mesh + instrinsic(图像坐标系到像素坐标系) + mask,在数据量不充足的情况下进行弱监督。
主要做的贡献如下(可能之前有人已提出):
- Encoder and Regression
- Projection and Mask
- Dataset
s
是缩放参数,R
旋转参数,t
是平移参数。def forward(self, x):
if (self.input_option):
x = self.conv11(x)
else:
x = self.conv1(x[:,0:3])
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
xs = self.fc(x)
xs = xs + self.mean
scale = xs[:,0] # image space to pixel space
trans = xs[:,1:3]
rot = xs[:,3:6] # 全局旋转(mano的旋视角)
theta = xs[:,6:12] #
beta = xs[:,12:]
x3d = rot_pose_beta_to_mesh(rot,theta,beta)
x = trans.unsqueeze(1) + scale.unsqueeze(1).unsqueeze(2) * x3d[:,:,:2]
x = x.view(x.size(0),-1)
#x3d = scale.unsqueeze(1).unsqueeze(2) * x3d
#x3d[:,:,:2] = trans.unsqueeze(1) + x3d[:,:,:2]
return x, x3d
3D Hand Shape and Pose from Images in the Wild
标签:recovery 部分 2018年 视角 layer 恢复 and str res
原文地址:https://www.cnblogs.com/wjy-lulu/p/13186619.html