About the depth-boundary consistency loss
sunnyHelen opened this issue · comments
Thank you for sharing your great work.
I have one question about the implementation of your loss function. For depth-boundary consistency loss, I think you realize it as a class there. But I found it isn't the same as the formulation you use in your paper. It seems like one the first term and without a minus sign. I'm a little confused and please help me figure it out.
Line 266 in 9206fb0
Hello,
Indeed, you are right, the loss I put in my code was a previous version, I will update it shortly. Thank you for your notice !
I solved this issue in commit 18672e1, minus signs may be written with torch.abs but they are the same in the end as terms are non positive.