发表机构
Trinity College Dublin; Dolby Laboratories（都柏林三一学院; 杜比实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TruncGradGS通过分段截断梯度公式解决3D高斯溅射的梯度消失问题，在静态、动态场景及多初始化方式下均提升性能，还提出动态高斯溅射基准新数据集。
AI 中文摘要
3D高斯溅射已成为新视图合成的事实上的场景表示，但从视觉输入中稳健学习3D高斯基元仍具挑战性。标准优化依赖基于梯度的更新，而常见问题是梯度消失现象：远离高斯基元的像素对基元属性的梯度幅值会减小，导致场景重建次优。本文提出一种分段截断梯度公式的方法来解决梯度消失问题，提升优化稳定性和初始化鲁棒性。研究表明，该方法在随机和COLMAP初始化下均能持续改进3D高斯溅射，且可泛化到静态和动态高斯溅射场景。作为副产品，本文还探讨了当前动态场景基准的局限性，并引入了一个用于动态高斯溅射基准测试的合成3D场景新数据集。在公共基准和本文提出的数据集的静态、动态设置中，均验证了所提方法的有效性。
英文摘要
3D Gaussian Splatting has become a de facto scene representation for novel view synthesis, yet robustly learning 3D Gaussian primitives from visual input remains challenging. Standard optimization relies on gradient-based updates, but a common issue is the gradient vanishing phenomenon: a pixel far from a Gaussian primitive often has diminishing gradient magnitudes to influence primitive attributes, resulting in suboptimal scene reconstruction. In this paper, we propose a method to address gradient vanishing with a piecewise truncated gradient formulation that improves the optimization stability and robustness to initializations. We show that our method consistently improves 3D Gaussian Splatting with random and COLMAP initializations while being generalizable across static and dynamic Gaussian Splatting. As a by-product, we also examine the limitations of current benchmarks for dynamic scenes, and introduce a novel dataset for benchmarking dynamic Gaussian Splatting using synthetic 3D scenes. We demonstrate the effectiveness of our method in both static and dynamic settings for the public benchmarks and our proposed dataset.
CommentsAccepted at Pacific Graphics 2026
