Open Tony-Hou opened 2 years ago
I don't understand this place very well,too. Why do it to set 3 times the depth_loss, and it seems that this depth_loss only supervises the depth predicted by the key frame. I now want to use the point cloud to complete the predicted depth of the image, but it seems It can only complete the depth predicted by the key frame frame.
self.depth_channels = int( (self.dbound[1] - self.dbound[0]) / self.dbound[2])