用惯性体积指导点云优化，提升3D高斯溅射重建质量
Refining Gaussian Splatting: A Volumetric Densification Approach
- 基于高斯函数的惯性体积引导点云精炼
- 在Mip-NeRF 360上优于原始3DGS，多场景表现更优
- 适合关注3D重建质量与点管理的视觉研究者
在3D高斯溅射（3DGS）中实现高质量新视角合成通常依赖于有效的点原语管理。自适应密度控制（ADC）过程通过自动化稠密化与剪枝来解决该问题。然而，原始3DGS的稠密化策略存在明显不足。本文提出一种新的密度控制方法，利用每个高斯函数的惯性体积来指导精炼过程。此外，我们研究了传统结构从运动（SfM）与深度图像匹配（DIM）方法在点云初始化中的影响。在Mip-NeRF 360数据集上的大量实验表明，所提方法在重建质量上超越3DGS，对多种场景均表现出良好性能。
原文摘要 · Abstract (English)
Achieving high-quality novel view synthesis in 3D Gaussian Splatting (3DGS) often depends on effective point primitive management. The underlying Adaptive Density Control (ADC) process addresses this issue by automating densification and pruning. Yet, the vanilla 3DGS densification strategy shows key shortcomings. To address this issue, in this paper we introduce a novel density control method, which exploits the volumes of inertia associated to each Gaussian function to guide the refinement process. Furthermore, we study the effect of both traditional Structure from Motion (SfM) and Deep Image Matching (DIM) methods for point cloud initialization. Extensive experimental evaluations on the Mip-NeRF 360 dataset demonstrate that our approach surpasses 3DGS in reconstruction quality, delivering encouraging performance across diverse scenes.
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。