FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

TL;DR

FlowScene is a novel multimodal graph-based generative model that produces high-fidelity, style-coherent indoor scenes with fine-grained control over object geometry and appearance, outperforming existing methods.

Contribution

It introduces a tri-branch model with a rectified flow mechanism for collaborative scene generation, enabling detailed control and style consistency in indoor scene synthesis.

Findings

Outperforms baselines in realism and style coherence

Enables fine-grained control over object attributes

Achieves better alignment with human preferences

Abstract

Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook object-level control and often fail to enforce scene-level style coherence. Graph-based formulations offer higher controllability over objects and inform holistic consistency by explicitly modeling relations, yet existing methods struggle to produce high-fidelity textured results, thereby limiting their practical utility. We present FlowScene, a tri-branch scene generative model conditioned on multimodal graphs that collaboratively generates scene layouts, object shapes, and object textures. At its core lies a tight-coupled rectified flow model that exchanges object information during generation, enabling collaborative reasoning across the graph. This enables fine-grained control of objects' shapes, textures, and relations while enforcing scene-level style coherence across structure and appearance. Extensive experiments show that FlowScene outperforms both language-conditioned and graph-conditioned baselines in terms of generation realism, style consistency, and alignment with human preferences.