Thank you for this awesome work.
I am interested in reproducing figure 9 where you constrain ges to about the same number of splats as the reference implementation. How to constraint the training to reproduce the results?
hey , to do that you have to play with the hyperparameters of Gaussians to make it have fewer components , basically you set the densify_grad_threshold = 0.0004
Thank you for this awesome work. I am interested in reproducing figure 9 where you constrain ges to about the same number of splats as the reference implementation. How to constraint the training to reproduce the results?
Thx and best, Janusch