use implicit keypoints equivariance loss LE，这里训练的GT是怎么获取到的？

[zdyshine]

感谢分享的工作，想请问训练的gt是怎么获取的？

[zzzweakman]

您好，您可以查阅Face Vid2Vid论文的3.4节，或者在它的补充材料中找到更详细的说明，下面是关于L_E的描述:This loss ensures the consistency of image-specific keypoints xd,k. For a valid keypoint, when applying a 2D transformation to the image, the predicted keypoints should change according to the applied transformation. Since we predict 3D instead of 2D keypoints, We use an orthographic projection to project the keypoints to the image plane before computing the loss.