Closed jiadingfang closed 1 year ago
Rank loss and assign loss mentioned in our paper are important for training our network. If only use photometric loss, the training process would be unstable.
Thanks for the suggestions! Questions about the depths in two regularization losses: are they (e.g. $D_s$, $d_i$) actual depths or normalized disparities?
They are normalized disparities.
Hi,
Per your hint for training at https://github.com/yxuhan/AdaMPI/issues/4#issuecomment-1214975556, I used the same photometric losses in MINE to try to train AdaMPI from scratch on the downsampled LLFF dataset that MINE provides. However, I had Nan errors some time into the training (not immediately). Have you spotted any Nan errors in the training? Do you have any suggestions handling them?
Thanks, JD