About the static training stage about 4dgaussians

[guanjunwu]

Hi, this is my understanding:
In some cases without SfM points initialization, training 4D-GS directly may cause difficulty in convergence. Optimizing 3D Gaussians for warm-up enjoys: (a) making some 3D Gaussians stay in the dynamic part, which releases the pressure of large deformation learning by 4D Gaussians. (b) learning proper 3D Gaussians $\mathcal{G}$ and suggesting deformation fields paying more attention to the dynamic part .
(c) avoiding numeric errors in optimizing the Gaussian deformation network $\mathcal{F}$ and keeping the training process stable. Results in paper shows that if we train our model without the warm-up coarse stage, the rendering quality will suffer.
And full version will be updated in Arxiv paper soon.