arXiv 2605.120722026-09-22cs.CV

PairDropGS: 基于配对 Dropout 引起的一致性正则化的稀疏视角高斯点云法

PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

School of Computer Science, Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学深圳校区计算机科学学院，中国）；Pengcheng Laboratory, Shenzhen, China（鹏城实验室，中国）；Smart Coding Institute, Pengcheng Laboratory, Shenzhen, China（鹏城实验室智能编码研究所，中国）；School of Computer Science, Harbin Institute of Technology, Harbin, China（哈尔滨工业大学计算机科学学院，中国）

Hantang Li, Qiang Zhu, Xiandong Meng, Xingtao Wang, Debin Zhao, Xiaopeng Fan

备注：: The methodological design is flawed, the experimental results are insufficient, and there are issues regarding the authors' affiliations and authorship

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出PairDropGS，通过配对Dropout引起的一致性正则化改进稀疏视角高斯点云法，提升训练稳定性与重建质量，同时保持方法的简洁性和易用性。

摘要：

基于Dropout的稀疏视角3D高斯点云法（3DGS）通过在训练过程中随机抑制高斯素体来缓解过拟合。现有方法主要集中在设计日益复杂的Dropout策略，但忽略了不同被抑制的高斯子集之间产生的不一致。这种忽视常导致重建不稳定和高斯表示学习不充分。本文从一致性正则化角度重新审视基于Dropout的稀疏视角3DGS，并提出PairDropGS，一种用于稀疏视角高斯点云法的配对Dropout引起的一致性正则化框架。具体而言，PairDropGS首先从共享的高斯场中构建一对被抑制的高斯子集，并设计低频一致性正则化以约束它们的低频渲染结构。该设计促使共享的高斯场在不同随机Dropout下保持稳定的场景布局和粗略几何，同时避免对模糊的高频细节施加过多约束。此外，我们引入了一种渐进的一致性调度策略，逐步加强一致性正则化以提高训练的稳定性和重建的鲁棒性。在广泛使用的稀疏视角基准上进行了大量实验，结果表明PairDropGS在训练稳定性方面表现优异，显著优于现有基于Dropout的3DGS方法在重建质量上的表现，同时展现出简洁性和插件式改进基于Dropout优化的特性。

英文摘要：

Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existing methods mainly focus on designing increasingly sophisticated dropout strategies, while they overlook the resulting inconsistencies among different dropped Gaussian subsets. This oversight often leads to unstable reconstruction and suboptimal Gaussian representation learning.In this paper, we revisit dropout-based sparse-view 3DGS from a consistency regularization perspective and propose PairDropGS, a Paired Dropout-induced Consistency Regularization framework for sparse-view Gaussian splatting. Specifically, PairDropGS first constructs a pair of the dropped Gaussian subsets from a shared Gaussian field and designs a low-frequency consistency regularization to constrain their low-frequency rendered structures. This design encourages the shared Gaussian field to preserve stable scene layout and coarse geometry under different random dropouts, while avoiding excessive constraints on ambiguous high-frequency details. Moreover, we introduce a progressive consistency scheduling strategy to gradually strengthen the consistency regularization during training for stability and robustness of reconstruction. Extensive experiments on widely-used sparse-view benchmarks demonstrate that PairDropGS achieves superior training stability, significantly outperforms existing dropout-based 3DGS methods in reconstruction quality, while exhibiting the simplicity and plug-and-play nature for improving dropout-based optimization.

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。