Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation

The paper introduces a large‑scale synthetic data pipeline built on Unreal Engine to generate action‑conditioned, multi‑view video for training world models. The system operates in two stages: real‑time physics simulation records trajectories, then offline rendering produces high‑quality video. It includes a distributed production framework with task partitioning, automated filtering, and a 25‑server cluster, yielding over 2,600 hours of 1080p and 6,000 hours of 720p video from 429 levels and 40 characters.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• diffusion