Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting
By: Xiaobin Deng , Qiuli Yu , Changyu Diao and more
Potential Business Impact:
Makes 3D pictures smaller without losing detail.
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.
Similar Papers
Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation
CV and Pattern Recognition
Makes 3D pictures look more real and clear.
RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS
CV and Pattern Recognition
Makes 3D pictures ignore moving things and changing light.
Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering
CV and Pattern Recognition
Makes 3D pictures look more real and detailed.