通过点云上采样提升3D高斯溅射的初始质量，改善场景重建效果。
Optimizing 3D Gaussian Splatting via Point Cloud Upsampling
- 采用多种上采样方法优化初始点云分布
- 深度引导方法在无纹理区域表现更优
- 不同方法适合不同场景类型，提供选型参考
3D高斯溅射（3DGS）依赖初始种子点质量，本文评估了线性插值、三角插值、基于样条的表面重建、移动最小二乘拟合及基于Voronoi的点生成等点云上采样方法。研究还提出一种深度图引导的点提升方法，以保持与运动恢复结构（SfM）重建的几何一致性。在Mip-NeRF360和Replica数据集上的实验表明，表面重建方法在有机细节丰富的场景中表现更佳，而简单插值更适合分段平滑的场景。深度引导方法能有效在全场景（尤其无纹理区域）添加几何感知点。结果为根据场景特征和计算约束选择合适上采样策略提供了初步实践指导，深化了对点云初始化影响3DGS质量的理解。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) is a technique for creating and rendering 3D scenes, however its performance depends heavily on the quality of initial seed points. To improve 3DGS initialization, this study presents and evaluates several point cloud upsampling approaches: linear interpolation, triangular interpolation, spline-based surface reconstruction, moving least squares surface fitting, and Voronoi-based point generation. Additionally, this research introduces a depth-guided point lifting method that leverages depth maps to maintain geometric consistency with Structure-from-Motion (SfM) reconstructions. Through extensive experiments on the Mip-NeRF360 and Replica datasets, the proposed methods demonstrate improvements in reconstruction quality across diverse scene types. Results indicate that different upsampling strategies excel in different scenarios: surface reconstruction methods perform better with organic, detailed scenes, while simpler interpolation approaches are more suited for scenes dominated by piecewise-smooth geometries. In comparison, the depth-guided approach shows promise for adding geometry-aware points across the entire scene, importantly in texture-less regions. These findings, which provide preliminary practical guidelines for selecting appropriate upsampling methods based on scene characteristics and computational constraints, advances the understanding of how point cloud initialization affects 3DGS quality.
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。