Paper Overview
Research Area: Computer Vision Authors: Rafal Karp, Gene Liu, Shih-Hsin Li, Eric Courtemanche, Shengze Wang, Josef Spjut, David Pankratz, Mischa Kolbe, Michael Stengel, Sven Elflein, Adam Grygielski, Liwen Wu, Anjul Patney Published: 2026-11-02 arXiv: 2611.03626
Abstract
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 the generated data directly in training-friendly formats, reducing intermediate storage, preparation time, and manual processing. This report describes the overall system design, including the platform's assets, plugins, and their capabilities, and explains how they work together to generate diverse synthetic gameplay data.
--- *Auto-collected on 2026-11-04*