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
I would like to ask is my understanding correct or I miss sth?
In my opinion, they use opacity and gradient masks to reduce the impact of immature splats on pose estimates. Because opacity depends on the covariance of ellipsoids that define a single gaussian (that's describes their uncertainty), while gradient masks capture high-contrast parts of an image (e.g., edges).
In the paper it's said:
We further <...> penalise non-edge or low-opacity pixels
In this sense, they are providing L1-loss as the residual, and then apply opacity and gradient mask as it's done in the code.
To my understanding, in the code, the tracking loss is opacity * L1 loss * a complicated mask (silhouetee) , but in the paper, it is simply L1 loss.
In the code
MonoGS/utils/slam_utils.py
Line 63 in b9f8b66
where the
viewport.grad_mask
is computed hereMonoGS/utils/camera_utils.py
Line 114 in b9f8b66
But in the paper, the tracking loss is simply
![image](https://private-user-images.githubusercontent.com/32609259/329195613-800fbc28-8835-4b39-b179-8897d18cab70.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.je_hFuXt3aWV9rYPjyyLbVtSMaMrY5MyYEuN15okYxM)
I would like to ask is my understanding correct or I miss sth?
The text was updated successfully, but these errors were encountered: