稀疏视角高斯溅射中的锚点丢弃与球谐函数方法

摘要

近期基于3D高斯泼溅（3DGS）的Dropout方法通过随机置零高斯透明度来解决稀疏视角下的过拟合问题。然而，我们发现这类方法存在邻域补偿效应：被丢弃的高斯分布常被其邻近单元补偿，从而削弱了正则化效果。此外，现有方法忽视了高阶球谐系数（SH）对过拟合的贡献。针对这些问题，我们提出DropAnSH-GS——一种新颖的基于锚点的Dropout策略。该方法不再独立丢弃高斯单元，而是随机选取部分高斯单元作为锚点，同步移除其空间邻域。这种机制有效破坏了锚点附近的局部冗余，促使模型学习更具鲁棒性的全局感知表征。进一步地，我们将Dropout扩展至颜色属性，通过随机丢弃高阶SH系数将外观信息集中至低阶SH。该策略不仅能有效抑制过拟合，还可通过SH截断实现训练后模型的灵活压缩。实验结果表明，DropAnSH-GS以可忽略的计算开销显著优于现有Dropout方法，并能无缝集成到各类3DGS变体中提升其性能。项目网站：https://sk-fun.fun/DropAnSH-GS

English

Recent 3D Gaussian Splatting (3DGS) Dropout methods address overfitting under sparse-view conditions by randomly nullifying Gaussian opacities. However, we identify a neighbor compensation effect in these approaches: dropped Gaussians are often compensated by their neighbors, weakening the intended regularization. Moreover, these methods overlook the contribution of high-degree spherical harmonic coefficients (SH) to overfitting. To address these issues, we propose DropAnSH-GS, a novel anchor-based Dropout strategy. Rather than dropping Gaussians independently, our method randomly selects certain Gaussians as anchors and simultaneously removes their spatial neighbors. This effectively disrupts local redundancies near anchors and encourages the model to learn more robust, globally informed representations. Furthermore, we extend the Dropout to color attributes by randomly dropping higher-degree SH to concentrate appearance information in lower-degree SH. This strategy further mitigates overfitting and enables flexible post-training model compression via SH truncation. Experimental results demonstrate that DropAnSH-GS substantially outperforms existing Dropout methods with negligible computational overhead, and can be readily integrated into various 3DGS variants to enhance their performances. Project Website: https://sk-fun.fun/DropAnSH-GS

稀疏视角高斯溅射中的锚点丢弃与球谐函数方法

Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting

摘要

Support