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
As to my understanding, all the Gaussians along the viewing ray direction will contribute to the Rasterisation. This would not be a issue in indoor test cases, and most of the outdoor cases, since the Gaussians grow along or near the direction of the camera.
But if there's a loop in an outdoor case. or U-turn. it may require the calculation to a majority of, if not all, Gaussians to render the view of the current scene.
I suppose there should be a limitation on the farest Gaussians to be considered, Plz kindly point out if there's any.
The text was updated successfully, but these errors were encountered:
Please correct me if i'm wrong.
As to my understanding, all the Gaussians along the viewing ray direction will contribute to the Rasterisation. This would not be a issue in indoor test cases, and most of the outdoor cases, since the Gaussians grow along or near the direction of the camera.
But if there's a loop in an outdoor case. or U-turn. it may require the calculation to a majority of, if not all, Gaussians to render the view of the current scene.
I suppose there should be a limitation on the farest Gaussians to be considered, Plz kindly point out if there's any.
The text was updated successfully, but these errors were encountered: