Existing diffusion-based 3D scene generation methods primarily operate in 2D image/video latent spaces, which makes maintaining cross-view appearance and geometric consistency inherently challenging. To bridge this gap, we present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space. Central to our approach is the 3D Unified Representation Autoencoder (3D-URAE); it leverages pretrained 3D foundation models and augments their geometry-centric nature by injecting appearance and distilling semantics into a unified 3D latent space. Furthermore, we introduce token-level Cross-View-Correspondence (CVC) consistency loss to explicitly enforce structural alignment across views, and propose Manifold-Drift Forcing (MDF) to mitigate train-inference exposure bias and shape a robust 3D manifold by mixing drifted and original representations. Comprehensive experiments demonstrate that OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods. Our code will be available at https://github.com/SensenGao/OneWorld.
@article{arxiv.2603.16099,
title = {OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder},
author = {Sensen Gao and Zhaoqing Wang and Qihang Cao and Dongdong Yu and Changhu Wang and Tongliang Liu and Mingming Gong and Jiawang Bian},
journal= {arXiv preprint arXiv:2603.16099},
year = {2026}
}