Perpetual 3D scene generation aims to produce long-range and coherent 3D view sequences, which is applicable for long-term video synthesis and 3D scene reconstruction. Existing methods follow a "navigate-and-imagine" fashion and rely on outpainting for successive view expansion. However, the generated view sequences suffer from semantic drift issue derived from the accumulated deviation of the outpainting module. To tackle this challenge, we propose ScenePainter, a new framework for semantically consistent 3D scene generation, which aligns the outpainter's scene-specific prior with the comprehension of the current scene. To be specific, we introduce a hierarchical graph structure dubbed SceneConceptGraph to construct relations among multi-level scene concepts, which directs the outpainter for consistent novel views and can be dynamically refined to enhance diversity. Extensive experiments demonstrate that our framework overcomes the semantic drift issue and generates more consistent and immersive 3D view sequences.
Pipeline of ScenePainter. We propose a two-stage framework that first constructs scene concept relations with the graph structure SceneConceptGraph, and further aligns the outpainting model with the scene-specific prior during the ongoing painting process.
@misc{xia2025scenepaintersemanticallyconsistentperpetual,
title={ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment},
author={Chong Xia and Shengjun Zhang and Fangfu Liu and Chang Liu and Khodchaphun Hirunyaratsameewong and Yueqi Duan},
year={2025},
eprint={2507.19058},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2507.19058},
}