通过瓦片局部的指令协同，让3D高斯点云渲染快7.76倍。
Local-GS: Accelerating 3D Gaussian Splatting via Tile-Local Warp Coherence
- 按SIMT执行边界分块高斯点，减少指令发散
- 在深度混合场景实现7.76倍加速，质量不变
- 可直接插入现有流程，适配各类3DGS模型
3D高斯点云（3DGS）通过密集分布的各向异性3D高斯基元实现了实时新视角合成。然而，高斯点的不规则空间分布常导致GPU利用率低下，因线程束发散和冗余计算降低渲染效率。为此，本文提出局部协同渲染范式Local-GS，将高斯基元组织方式从场景几何改为贴合SIMT（单指令多线程）执行边界。具体包含三个协同阶段：预计算级（在瓦片级别预先计算共享参数）、剔除级（丢弃无贡献的线程束）、融合级（以统一指令流替代逐像素分支）。在多个数据集上的广泛测试表明，Local-GS在不损失质量的前提下显著提升效率，作为即插即用优化，为所有测试基线带来额外性能增益，在深度混合场景达到7.76倍加速。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has significantly advanced real-time novel view synthesis by representing scenes as dense collections of anisotropic 3D Gaussian primitives. However, the irregular spatial distribution of Gaussians often leads to poor GPU utilization, as warp divergence and redundant computation degrade rendering performance. To address this, we present Local-GS, a warp-coherent rendering paradigm that, organizes Gaussian primitives with respect to SIMT (Single Instruction, Multiple Threads) execution boundaries rather than scene geometry. Specifically, we propose three warp-coherent stages: a hoisting stage that precomputes shared parameters at tile level, a culling stage that discards warps with no contribution, and a blending stage that replaces per-pixel branching with a uniform instruction stream. Across extensive benchmarks on multiple datasets, Local-GS improves efficiency without compromising quality. As a plug-and-play optimization, it provides additional performance gains to all tested baselines, culminating in a $7.76\times$ speedup on Deep Blending 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。