XPR让点云渲染快速跨平台部署，只需少量代码。
XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer
- 高阶接口分离渲染逻辑与通用流程，支持快速开发新方法。
- 仅用数百行代码实现3DGS等三种渲染方法，编译到多硬件平台。
- 适合想快速实验点云渲染的开发者和研究者。
基于点的可微渲染支撑现代3D重建、新视角合成与学习型图形管线，但开发新方法常需大量底层实现、硬件专用内核及手动编写反向传播，限制了快速原型设计、可复现性、探索与跨平台部署。本文提出XPR，一个可扩展的跨平台点基可微渲染框架。XPR引入高层编程接口，将方法特定逻辑与共享渲染流程分离，用户仅需数行代码即可实现新方法。其管道将渲染分解为模块化、静态形状的并行操作，可通过跨平台编译器降级至GPU、TPU、CPU及其他机器学习加速器。我们展示了3DGS、3DGUT和LinPrim的实现，仅需数百行Python代码，均可通过XLA编译器部署到多种硬件平台。结果表明，XPR使新兴点基可微渲染系统具备快速实验与可移植执行能力。
原文摘要 · Abstract (English)
Point-based differentiable rendering underpins modern 3D reconstruction, novel-view synthesis, and learning-based graphics pipelines, but developing new rendering methods often requires extensive low-level implementation, hardware-specific kernels, and manually written backward passes. This limits rapid prototyping, reproducibility, exploration, and deployment, especially across diverse hardware platforms. This paper presents XPR, an extensible cross-platform framework for point-based differentiable rendering. XPR introduces a high-level programming interface that separates method-specific logic from the shared rendering pipeline, allowing users to implement new methods in a few lines of code. Its pipeline decomposes rendering into modular, statically shaped parallel operations that can be lowered by a cross-platform compiler to GPUs, TPUs, CPUs, and other ML accelerators. We demonstrate implementations of 3DGS, 3DGUT, and LinPrim, with only a few 100s lines of Python code, each of which can be compiled to a range of hardware platforms with the XLA compiler. These results show that XPR enables fast experimentation and portable execution for emerging point-based differentiable rendering systems.
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。