What is the EDGS initialization method different from adopting a dense point cloud using the MVS method directly?

[VISjudy]

Thanks to the author for his excellent work! There is related work doing 3DGS initialization using dense point clouds generated by the MVS method, and your approach uses Roma feature matching and triangulation to reconstruct denser point clouds by sampling portions of all images.

I was wondering if there is any difference between your method and using MVS initialization?
Is it an improvement in efficiency or is the reconstructed point cloud in 3D space of higher quality?

How long does it take to reconstruct a dense point cloud using your method?

[venite-xjc]

@VISjudy Hello! I'm interested in the research you mentioned on dense initialization using the MVS method. Could you please tell me about the relevant papers? Thank you very much!