Python库实现每秒百万级3D批量渲染，加速强化学习训练。
PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS
- 基于Panda3D引擎优化批量渲染，支持纯Python快速搭建场景。
- 简单场景下达100万帧/秒，相比常规方法提速最高1000倍。
- 适合需要高速3D仿真但不想用复杂C++框架的研究者。
从像素进行强化学习常受3D渲染环境性能与复杂性的制约。研究者在高速低层引擎与慢速易用的Python框架间面临权衡。为此，我们提出PyBatchRender，一个基于Panda3D引擎的Python高吞吐批量3D渲染库，在简单场景下可实现超过100万帧/秒的渲染速度。通过优化批量渲染，其性能相较常规方法提升最高达1000倍。该库作为物理无关的渲染器，适用于从像素出发的强化学习任务，相比专用库更具灵活性，比典型游戏引擎封装更易部署，速度媲美顶尖的C++引擎如Madrona。用户仅需数十行代码即可在纯Python中创建自定义场景，实现大规模AI训练的快速原型设计。开源且易于集成，旨在降低高性能3D仿真门槛。项目地址：https://github.com/dolphin-in-a-coma/PyBatchRender。
原文摘要 · Abstract (English)
Reinforcement learning from pixels is often bottlenecked by the performance and complexity of 3D rendered environments. Researchers face a trade-off between high-speed, low-level engines and slower, more accessible Python frameworks. To address this, we introduce PyBatchRender, a Python library for high-throughput, batched 3D rendering that achieves over 1 million FPS on simple scenes. Built on the Panda3D game engine, it utilizes its mature ecosystem while enhancing performance through optimized batched rendering for up to 1000X speedups. Designed as a physics-agnostic renderer for reinforcement learning from pixels, PyBatchRender offers greater flexibility than dedicated libraries, simpler setup than typical game-engine wrappers, and speeds rivaling state-of-the-art C++ engines like Madrona. Users can create custom scenes entirely in Python with tens of lines of code, enabling rapid prototyping for scalable AI training. Open-source and easy to integrate, it serves to democratize high-performance 3D simulation for researchers and developers. The library is available at https://github.com/dolphin-in-a-coma/PyBatchRender.
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。