解决稀疏视角下3D高斯点云重建的过拟合与欠拟合问题。
D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction
- 根据深度和密度自适应剔除冗余点，防止近处过拟合。
- 远距离区域通过定向监督提升重建质量，减少空白区。
- 提出新评估指标，量化高斯分布稳定性，适合稀疏重建场景。
近期3D高斯点云拼贴（3DGS）技术实现了实时、高保真新视角合成，具备显式三维表示。但在稀疏视角条件下，性能退化与不稳定问题依然显著。本文识别出两个关键失败模式：相机附近高斯密度过高导致过拟合，远距离区域覆盖不足引发欠拟合。为此，我们提出统一框架D²GS，包含两项核心组件：深度-密度引导的丢弃策略（Depth-and-Density Guided Dropout），通过密度与深度自适应掩码抑制冗余高斯点；以及距离感知保真度增强模块（Distance-Aware Fidelity Enhancement），通过针对性监督提升远场区域重建质量。此外，我们引入新评估指标以量化学习到的高斯分布稳定性，揭示稀疏视角下3DGS的鲁棒性。在多个数据集上的大量实验表明，本方法显著提升了稀疏视角下的视觉质量与鲁棒性。
原文摘要 · Abstract (English)
Recent advances in 3D Gaussian Splatting (3DGS) enable real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations. However, performance degradation and instability remain significant under sparse-view conditions. In this work, we identify two key failure modes under sparse-view conditions: overfitting in regions with excessive Gaussian density near the camera, and underfitting in distant areas with insufficient Gaussian coverage. To address these challenges, we propose a unified framework D$^2$GS, comprising two key components: a Depth-and-Density Guided Dropout strategy that suppresses overfitting by adaptively masking redundant Gaussians based on density and depth, and a Distance-Aware Fidelity Enhancement module that improves reconstruction quality in under-fitted far-field areas through targeted supervision. Moreover, we introduce a new evaluation metric to quantify the stability of learned Gaussian distributions, providing insights into the robustness of the sparse-view 3DGS. Extensive experiments on multiple datasets demonstrate that our method significantly improves both visual quality and robustness under sparse view conditions. The project page can be found at: https://insta360-research-team.github.io/DDGS-website/.
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。