3D高斯溅射无需精确体渲染，高效优化仍可超越理论更优方案。
Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?
- 用近似体渲染替代精确算法，提升训练与推理效率。
- 低数量高斯时精度提升明显，但多数情况仍优于精确方法。
- 适合追求实时生成与快速训练的3D重建应用者阅读。
自提出以来，3D高斯溅射（3DGS）已成为捕捉场景3D表示的重要基准方法，可在实时新视角合成中实现高视觉质量与快速训练。神经辐射场（NeRFs）在体渲染理论基础上采用逐射线追踪方式，而3DGS虽共享相似成像模型，却结合了体渲染与基元光栅化的优点，形成混合渲染方案。其性能优势源于一系列近似处理。本文深入分析原3DGS方案中的各类近似与假设，发现虽然更精确的体渲染在基元数量较少时能提升效果，但得益于高效的优化与大量高斯分布，3DGS仍能超越精确体渲染方案。
原文摘要 · Abstract (English)
Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray-marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in-depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.
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。