arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2511.13571cs.CV

Opt3DGS：基于自适应探索与曲率感知利用的3D高斯溅射优化方法

Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation

Ziyang Huang, Jiagang Chen, Jin Liu, Shunping Ji

备注：
Accepted at AAAI 2026 as a Conference Paper
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对3DGS优化易陷局部最优、收敛质量不足的问题，本文提出Opt3DGS两阶段优化框架，通过自适应SGLD全局探索与曲率引导的Adam局部利用，在不改动3DGS底层表示的前提下实现了SOTA渲染质量。

摘要：

3D Gaussian Splatting（3DGS，三维高斯溅射）已成为新视角合成领域的主流框架，但其核心优化问题仍未得到充分探究。本文指出3DGS优化存在两大关键问题：易陷入次优局部最优、收敛质量不足。针对上述问题，我们提出Opt3DGS鲁棒框架，通过自适应探索与曲率引导利用的两阶段优化流程改进3DGS。探索阶段采用自适应加权随机梯度朗之万动力学（SGLD）方法增强全局搜索能力，以跳出局部最优；利用阶段采用局部拟牛顿方向引导的Adam优化器，借助曲率信息实现精准高效收敛。在多个基准数据集上开展的大量实验表明，Opt3DGS无需修改3DGS底层表示，仅通过优化其训练流程即可达到当前最优的渲染质量。

英文摘要：

3D Gaussian Splatting (3DGS) has emerged as a leading framework for novel view synthesis, yet its core optimization challenges remain underexplored. We identify two key issues in 3DGS optimization: entrapment in suboptimal local optima and insufficient convergence quality. To address these, we propose Opt3DGS, a robust framework that enhances 3DGS through a two-stage optimization process of adaptive exploration and curvature-guided exploitation. In the exploration phase, an Adaptive Weighted Stochastic Gradient Langevin Dynamics (SGLD) method enhances global search to escape local optima. In the exploitation phase, a Local Quasi-Newton Direction-guided Adam optimizer leverages curvature information for precise and efficient convergence. Extensive experiments on diverse benchmark datasets demonstrate that Opt3DGS achieves state-of-the-art rendering quality by refining the 3DGS optimization process without modifying its underlying representation.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑