3D Gaussian Accelerated Ray Tracing: Fast training through particle-based backward propagation
作者: Laurent Vit, Oliver Batchelor, Richard Green
分类: cs.GR, cs.CV
发布日期: 2026-08-18
💡 一句话要点
提出3DGART以解决高效训练高质量光线追踪问题
🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)
关键词: 光线追踪 高斯渲染 训练优化 计算机图形学 实时渲染
📋 核心要点
- 现有的光线追踪高斯渲染方法在训练过程中面临像素中心的反向传播导致的线程争用和序列化问题,影响了效率。
- 论文提出的3DGART通过围绕高斯原语重组反向传播,利用保守的透视校正屏幕空间边界,减少了线程间的竞争。
- 在Mip-NeRF 360数据集上,3DGART相较于每像素基线实现了约3-3.5倍的训练速度提升,并且在质量上也有所改善。
📝 摘要(中文)
3D Gaussian Splatting使高斯原语成为实时新视角合成的高效表示,但其基于光栅化的形式依赖于屏幕空间近似,限制了准确的视角依赖排序及次级光线效果的整合。为了解决这些问题,论文提出了3DGART,一个实用的光线追踪高斯渲染训练框架。其核心思想是围绕原语而非像素重组反向传播,显著提高了训练速度和质量。实验表明,3DGART在Mip-NeRF 360上实现了约3-3.5倍的训练速度提升,同时保持了光线追踪的优势。
🔬 方法详解
问题定义:现有的光线追踪高斯渲染方法在训练时,像素中心的反向传播导致多个线程同时向同一原语参数累积梯度,造成严重的原子竞争和线程序列化,影响训练效率。
核心思路:论文的核心解决思路是围绕高斯原语重组反向传播过程,利用保守的透视校正屏幕空间边界,构建紧凑的中间缓冲区和瓦片-原语映射,使每个线程能够在其覆盖的像素上累积单个原语的贡献。
技术框架:整体架构包括数据预处理、原语映射构建、反向传播重组和梯度计算等模块。通过这些模块的协同工作,优化了训练过程。
关键创新:最重要的技术创新点在于将反向传播从竞争激烈的散射操作转变为结构化的聚集过程,这一设计显著提高了训练效率。
关键设计:在参数设置上,采用了保守的透视校正屏幕空间边界,并设计了紧凑的中间缓冲区,以支持高效的梯度计算和原语映射。
🖼️ 关键图片
📊 实验亮点
实验结果显示,3DGART在Mip-NeRF 360数据集上实现了约3-3.5倍的训练速度提升,相较于3DGRT实现了约4倍的速度提升,同时在图像质量上也有所改善,展示了其在实际应用中的潜力。
🎯 应用场景
该研究的潜在应用领域包括实时渲染、虚拟现实和计算机图形学等。通过提高光线追踪高斯渲染的训练效率,3DGART能够在更广泛的场景中实现高质量的图像合成,推动相关技术的发展与应用。
📄 摘要(原文)
3D Gaussian Splatting has made Gaussian primitives a highly efficient representation for real-time novel view synthesis, but its rasterisation-based formulation relies on screen-space approximations that limit accurate view-dependent ordering and the integration of secondary ray effects such as reflections, refractions, and shadows. Gaussian ray tracing addresses these limitations by evaluating explicit ray-primitive intersections, yet it remains costly to train. We observe that the main bottleneck is not ray traversal alone, but the pixel-centric backward propagation, where many threads concurrently accumulate gradients into the same primitive parameters, causing severe atomic contention and thread serialisation. We present 3DGART, a practical training framework for ray-traced Gaussian rendering. Our key idea is to reorganise backward propagation around primitives rather than pixels. Using conservative perspective-correct screen-space bounds, we build a compact intermediate buffer and a tile-primitive mapping that allows each thread to accumulate the contribution of one primitive over its covered pixels within a tile. This transforms gradient computation from a contention-heavy scatter operation into a structured gather-like process. On Mip-NeRF 360, 3DGART achieves an $\approx 3-3.5\times$ raw training speedup over per-pixel baseline and $\approx4 \times$ over 3DGRT on Mip-NeRF 360 while improving quality. More importantly, 3DGART makes fully ray-traced Gaussian training practical, reaching runtimes competitive with rasterisation-based pipelines while preserving benefits of ray tracing.