Score: 0

Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting

Published: November 21, 2025 | arXiv ID: 2511.16980v1

By: Xiaobin Deng , Qiuli Yu , Changyu Diao and more

Potential Business Impact:

Makes 3D pictures smaller without losing detail.

Business Areas:
A/B Testing Data and Analytics

3DGS employs a large number of Gaussian primitives to fit scenes, resulting in substantial storage and computational overhead. Existing pruning methods rely on manually designed criteria or introduce additional learnable parameters, yielding suboptimal results. To address this, we propose an natural selection inspired pruning framework that models survival pressure as a regularization gradient field applied to opacity, allowing the optimization gradients--driven by the goal of maximizing rendering quality--to autonomously determine which Gaussians to retain or prune. This process is fully learnable and requires no human intervention. We further introduce an opacity decay technique with a finite opacity prior, which accelerates the selection process without compromising pruning effectiveness. Compared to 3DGS, our method achieves over 0.6 dB PSNR gain under 15\% budgets, establishing state-of-the-art performance for compact 3DGS. Project page https://xiaobin2001.github.io/GNS-web.

Page Count
19 pages

Category
Computer Science:
CV and Pattern Recognition