【论文速递】Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data

英文标题：Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data

arXiv编号：2611.03626
作者：Rafal Karp, Gene Liu, Shih-Hsin Li
来源：arXiv
原文链接：https://arxiv.org/abs/2611.03626

中文摘要：
We present Isekai3D Synthetic Data Generation (SDG), a platform for simulating and capturing synthetic 3D gameplay for research in vision and world models, neural graphics, gameplay agents, and other applications. The platform combines reusable environment and character assets with Unreal Engine plugins in a two-stage workflow. First, world simulation generates gameplay while recording the world state, character movements, actions, and camera tracks needed for replay. Second, the recorded simulation is replayed to capture selected outputs, such as rendered video, images, and depth maps, at a specified resolution and frame rate under selected rendering and camera configurations. Separating simulation from capture allows the same recorded gameplay to produce multiple output variants without repeating the original simulation. Visual outputs are accompanied by frame-aligned camera, character, and action metadata. The platform uploads generated data directly in a training-friendly format, reducing intermediate storage, preparation time, and manual processing. This report describes the design of our overall system, including the platform's assets, plugins, and their functionality, explaining how they work together to generate diverse synthetic gameplay data.

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。