The use of loss for hard depth and soft depth starts at the moment
wangyuanbiubiubiu opened this issue · 1 comments
wangyuanbiubiubiu commented
I notice that each data has a different time to start using soft and hard depth loss, is this a big difference? Whether it can be considered that the generality of these losses is not so strong is a result of parameter adjustment
Fictionarry commented
Hi, in fact we use the same start times of hard and soft depths (0 and 1000, respectively) for all scenes in LLFF and DTU, containing 8+15 scenes. I think this cross-dataset consistency is sufficient to prove the generality.