search

ChikaYan / d2nerf

Apache License 2.0
181 stars 14 forks source link

The final results on camera_shadow dataset #11

Closed m-richa closed 11 months ago

m-richa commented 1 year ago

After training for 100000 steps, the static part still has hand shadows. Does it need to be trained more?

ChikaYan commented 1 year ago

Hi, usually the separation becomes fixed at quite early iterations, so 100k is definitely enough. May I ask what configuration did you use to train the model? Also please note that due to the strong view dependency of camera/hand in this dataset, it's sometimes quite difficult for the model to perfectly tell whether the shadow is a view-dependent effect or dynamic effect without any additional priors. Hence it is expected to have some artifacts in the separation.

Hope that helps!