Birth-death control for 3DGS uses a variational score instead of densification heuristics

arXivarXivPapers

Birth-death control for 3DGS uses a variational score instead of densification heuristics
arXiv / Quan Tran Hong, Long Nguyen-Chi and Binh T. Nguyen

Quan Tran Hong, Long Nguyen-Chi and Binh T. Nguyen present first-variation birth-death control for 3D Gaussian Splatting, replacing heuristic cloning, splitting and pruning with a variational score derived from the reconstruction loss. At each structural update the current Gaussian population is frozen, auxiliary mass coordinates are attached to each primitive, and the multi-view loss is differentiated with respect to those coordinates.

High-score Gaussians are selected as birth sites, while low-score, low-opacity Gaussians are removed. Integrated into 3DGS-MCMC, the score yields state-of-the-art reconstruction quality, with the most significant gains under tight Gaussian budgets. Code is on GitHub.