HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation

TL;DR

HetScene introduces a heterogeneity-aware, two-stage indoor scene generation framework that models primary and secondary objects separately for more realistic and complex dense indoor layouts.

Contribution

The paper proposes a novel two-stage generation method that explicitly accounts for object heterogeneity, improving the realism and scalability of dense indoor scene synthesis.

Findings

Successfully generates globally coherent structural layouts from text and spatial cues.

Decouples scene synthesis into structural and contextual stages for better realism.

Enhances the physical plausibility of generated indoor scenes.

Abstract

Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as homogeneous instances within a unified generation process. While effective for sparse and simplistic layouts, they struggle to model realistic layouts with dense object arrangements and complex spatial dependencies, leadingto limited scalability and degraded physical plausibility. To deal with these challenges, we revisit indoor layout generation from the perspective of structural heterogeneity and decompose the objects into primary objects and secondary objects according to their distinct roles in shaping a scene. Based on this decomposition, we propose HetScene, a heterogeneous two-stage generation framework that decouples indoor layout synthesis into Structural Layout Generation (SLG) and Contextual Layout Generation (CLG). SLG first generates globally coherent structural layouts with only primary objects conditioned on text descriptions, top-down binary room masks, and spatial relation graphs, establishing a stable global macro-skeleton of large core furniture.