HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909040364224512 |
|---|---|
| author | Chen, Zini Huang, Junming Zhang, Rong Xu, Jiamin Peng, Cheng Wang, Chi Xu, Weiwei |
| author_facet | Chen, Zini Huang, Junming Zhang, Rong Xu, Jiamin Peng, Cheng Wang, Chi Xu, Weiwei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13586 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation Chen, Zini Huang, Junming Zhang, Rong Xu, Jiamin Peng, Cheng Wang, Chi Xu, Weiwei Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.13586 |