用PyTorch抽象实现多卡高分辨率高斯点云重建
A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting
- 通过CUDA统一内存与NVLink分发参数和操作符，实现多卡自动并行
- 成功重建超10亿个高斯点的城市场景，是当前最优水平的25倍以上
- 代码零修改即可利用多卡资源，适合大规模3D重建研究者
高斯点云方法在真实世界神经重建中日益流行，但受限于计算与内存，难以扩展至大场景和高分辨率。本文提出一种多卡高斯点云重建方案，通过自研PyTorch后端，利用CUDA统一内存与NVLink将高斯参数和绘制操作符分布在多张GPU上。由于分布发生在操作符层面，模型代码无需显式跨设备通信。该后端将多张GPU抽象为一个统一的PyTorch设备，兼容其他原生PyTorch操作。实验展示可实现包含超过10亿个高斯点的城市场景重建，细节达到街级水平，数据量超过当前最优水平的25倍。
原文摘要 · Abstract (English)
Gaussian splatting methods have become increasingly popular for neural reconstruction of the real world. However, they are often limited in scale and resolution due to compute and memory constraints. We present a multi-GPU Gaussian splatting approach that scales reconstruction to higher resolutions and larger scenes while abstracting away the code complexity typically associated with distributing a model. To accomplish this, we propose a PyTorch backend that distributes the Gaussian parameters and splatting operators across GPUs via CUDA unified memory and NVLink. Because distribution occurs at the operator level, the model code requires no explicit cross-device communication. More broadly, the backend exposes multiple GPUs as an aggregate PyTorch device and supports other PyTorch operators. We demonstrate city-scale reconstructions with street-level detail consisting of over 1 billion Gaussian splats, more than 25 times as many as the current 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。