Papers
arxiv:2507.19058

ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment

Published on Jul 25
· Submitted by xiac24 on Jul 29
Authors:
,
,
,
,

Abstract

ScenePainter framework uses a hierarchical graph structure to ensure semantically consistent 3D scene generation by addressing the semantic drift problem in successive view expansion.

AI-generated summary

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. Project Page: https://xiac20.github.io/ScenePainter/.

Community

Paper author Paper submitter

We propose ScenePainter, which aims to generate semantically consistent yet visually diverse 3D view sequences starting from a single view. Project Page: https://xiac20.github.io/ScenePainter/.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.19058 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.19058 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.19058 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.