用梯度驱动的自然选择机制，自动压缩3D高斯点云并提升质量。
Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting
- 以渲染质量为目标，让梯度自动决定保留或删除高斯点。
- 在15%存储预算下，PSNR提升超0.6 dB，优于现有方法。
- 无需人工设定规则，适合追求高效3D重建的开发者。
3DGS使用大量高斯原语拟合场景，导致存储和计算开销巨大。现有剪枝方法依赖人工设计标准或引入额外可学习参数，效果不佳。为此，我们提出一种受自然选择启发的剪枝框架，将生存压力建模为作用于透明度的正则化梯度场，使优化梯度——由最大化渲染质量的目标驱动——自主决定保留或剪除高斯点。该过程完全可学习，无需人工干预。此外，我们引入具有有限透明度先验的透明度衰减技术，加速选择过程且不损害剪枝效果。与3DGS相比，在15%预算下，本方法实现超过0.6 dB的PSNR增益，达到紧凑型3DGS的最先进性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。