You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The original paper and implementation used two new loss functions like in 2DGS, one on the distance between gaussian splats and one on the normal-map. The latest code uses only the normal loss now. Why is that? I'm very curious on your findings on this.
The text was updated successfully, but these errors were encountered:
The original paper and implementation used two new loss functions like in 2DGS, one on the distance between gaussian splats and one on the normal-map. The latest code uses only the normal loss now. Why is that? I'm very curious on your findings on this.
The text was updated successfully, but these errors were encountered: