LiteGS通过软硬件协同设计，让3D高斯溅射训练快10倍以上。
LiteGS: A High-performance Framework to Train 3DGS in Subminutes via System and Algorithm Codesign
- 从计算、数据、算法三层协同优化训练流程
- 最高提速13.4倍，高质量重建训练时间降为原来的十分之一
- 适合追求快速3D重建的科研与工业用户
3D高斯溅射（3DGS）作为新兴的3D表示方法，仍面临训练成本高的问题。本文提出LiteGS，一个通过系统与算法协同设计的高性能训练框架，从底层计算、中层数据管理到顶层算法三方面进行系统优化。在计算层，设计基于warp的光栅化机制，结合两项硬件感知优化，显著降低梯度归约开销；在数据层，引入基于Morton编码的动态空间排序，实现高效‘聚类-剔除-紧凑’流水线，提升数据局部性，减少缓存未命中；在算法层，建立基于透明度梯度方差的新稠密化准则，配合更稳定的透明度控制机制，实现更精确的参数增长。实验表明，LiteGS相比原3DGS最高加速13.4倍，重建质量相当或更优；在轻量级模型上较当前SOTA快1.4倍；在高质量重建任务中创下新精度纪录，训练时间缩短一个数量级。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has emerged as promising alternative in 3D representation. However, it still suffers from high training cost. This paper introduces LiteGS, a high performance framework that systematically optimizes the 3DGS training pipeline from multiple aspects. At the low-level computation layer, we design a ``warp-based raster'' associated with two hardware-aware optimizations to significantly reduce gradient reduction overhead. At the mid-level data management layer, we introduce dynamic spatial sorting based on Morton coding to enable a performant ``Cluster-Cull-Compact'' pipeline and improve data locality, therefore reducing cache misses. At the top-level algorithm layer, we establish a new robust densification criterion based on the variance of the opacity gradient, paired with a more stable opacity control mechanism, to achieve more precise parameter growth. Experimental results demonstrate that LiteGS accelerates the original 3DGS training by up to 13.4x with comparable or superior quality and surpasses the current SOTA in lightweight models by up to 1.4x speedup. For high-quality reconstruction tasks, LiteGS sets a new accuracy record and decreases the training time by an order of magnitude.
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。