让3D高斯点云模型变小10倍，质量不降反而更快。
BOGausS: Better Optimized Gaussian Splatting
- 重新设计训练优化流程，精简高斯点数量与参数。
- 模型体积缩小10倍，渲染质量与原版无差别。
- 适合部署在移动端或实时应用的轻量级3D重建。
3D高斯点云（3DGS）为新视角合成提供了一种高效方案，可实现快速且高质量的渲染。尽管其复杂度低于神经辐射场（NeRF）等方法，但在保持高质量的前提下构建更小模型仍面临挑战。本研究对3DGS训练过程进行了细致分析，提出一种新的优化方法。所提出的更好优化高斯点云（BOGausS）方案可生成比原始3DGS轻十倍的模型，且无质量损失，显著优于当前最优水平，大幅提升了高斯点云的性能表现。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) proposes an efficient solution for novel view synthesis. Its framework provides fast and high-fidelity rendering. Although less complex than other solutions such as Neural Radiance Fields (NeRF), there are still some challenges building smaller models without sacrificing quality. In this study, we perform a careful analysis of 3DGS training process and propose a new optimization methodology. Our Better Optimized Gaussian Splatting (BOGausS) solution is able to generate models up to ten times lighter than the original 3DGS with no quality degradation, thus significantly boosting the performance of Gaussian Splatting compared to the state of the art.
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。