Loss and training of the Rigid Structure Reconstructor about geonet HOT 3 CLOSED

I mean maybe there should be a regularization on Depth to prevent "the all same depth output"?

from geonet.

1. Since we enforce the warping loss for both stages, including the rigid reconstruction part, identical depth prediction cannot lead to convergence in terms of optimization;
2. I think it depends on your network initialization. You can check whether most of the rigid flow points to coordinates out of the image plane. In that case, the warping loss doesn't give you reasonable supervision signal. Another way to debug it is to try different scaling coefficients of the posenet output or the depthnet output (

   GeoNet/geonet_nets.py

   Lines 10 to 11 in 5b17602

   	DISP_SCALING_RESNET50 = 5
   	DISP_SCALING_VGG = 10

   ). You can also visualize the warped images guided by rigid flow.

from geonet.

Thank you so much for your reply. I will try that.

from geonet.