提出新方法缓解稀疏视角下3D高斯点云过拟合问题
Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting
- 以锚点为中心同时移除邻近高斯点，打破局部冗余
- 随机丢弃高阶球谐系数，降低颜色过拟合风险
- 无需额外计算开销，可适配多种3DGS模型
近期的3D高斯点云（3DGS）Dropout方法通过随机置零高斯透明度来缓解稀疏视角下的过拟合。但我们发现这些方法存在邻近补偿效应：被丢弃的高斯点常被邻居补偿，削弱了正则化效果。此外，现有方法忽略了高阶球谐系数（SH）对过拟合的贡献。为此，我们提出新的基于锚点的Dropout策略DropAnSH-GS：不独立丢弃高斯点，而是随机选择部分高斯点作为锚点，并同时移除其空间邻近点。该策略有效破坏锚点附近的局部冗余，促使模型学习更鲁棒、全局感知的表示。此外，我们将Dropout扩展至颜色属性，随机丢弃高阶SH系数，使外观信息集中于低阶SH，进一步缓解过拟合，并可通过截断SH实现灵活的训练后模型压缩。实验表明，DropAnSH-GS显著优于现有方法，计算开销极小，且可无缝集成到多种3DGS变体中提升性能。
原文摘要 · Abstract (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
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。