通过分组训练加速3D高斯点云渲染，提升效率与质量。
Faster and Better 3D Splatting via Group Training
- 将高斯点分组统一优化，降低训练计算开销。
- 实现最高30%的收敛速度提升，保持高质量渲染效果。
- 适配主流3DGS框架，适合追求高效重建的研究者。
3D高斯点云（3DGS）作为新兴的视图合成技术，凭借其高斯原语表示，在高保真场景重建方面表现出强大能力。然而，大量原始点带来的计算开销严重制约了训练效率。为此，我们提出分组训练（Group Training）策略，将高斯点组织为可管理的组别，从而显著提升训练效率并改善渲染质量。该方法与现有3DGS框架（包括原始3DGS和Mip-Splatting）具有广泛兼容性，持续实现更快训练速度并维持卓越合成质量。大量实验表明，该简单有效的策略在多种场景下实现最高达30%的收敛速度提升，并带来更优的渲染效果。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, demonstrating remarkable capability in high-fidelity scene reconstruction through its Gaussian primitive representations. However, the computational overhead induced by the massive number of primitives poses a significant bottleneck to training efficiency. To overcome this challenge, we propose Group Training, a simple yet effective strategy that organizes Gaussian primitives into manageable groups, optimizing training efficiency and improving rendering quality. This approach shows universal compatibility with existing 3DGS frameworks, including vanilla 3DGS and Mip-Splatting, consistently achieving accelerated training while maintaining superior synthesis quality. Extensive experiments reveal that our straightforward Group Training strategy achieves up to 30\% faster convergence and improved rendering quality across diverse scenarios. Project Website: https://chengbo-wang.github.io/3DGS-with-Group-Training/
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。