Co-Layout: LLM-driven Co-optimization for Interior Layout
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915838916820992 |
|---|---|
| author | Xiang, Chucheng Bao, Ruchao Feng, Biyin Wu, Wenzheng Liu, Zhongyuan Guan, Yirui Liu, Ligang |
| author_facet | Xiang, Chucheng Bao, Ruchao Feng, Biyin Wu, Wenzheng Liu, Zhongyuan Guan, Yirui Liu, Ligang |
| contents | We present a novel framework for automated interior design that combines large language models (LLMs) with grid-based integer programming to jointly optimize room layout and furniture placement. Given a textual prompt, the LLM-driven agent workflow extracts structured design constraints related to room configurations and furniture arrangements. These constraints are encoded into a unified grid-based representation inspired by ``Modulor". Our formulation accounts for key design requirements, including corridor connectivity, room accessibility, spatial exclusivity, and user-specified preferences. To improve computational efficiency, we adopt a coarse-to-fine optimization strategy that begins with a low-resolution grid to solve a simplified problem and guides the solution at the full resolution. Experimental results across diverse scenarios demonstrate that our joint optimization approach significantly outperforms existing two-stage design pipelines in solution quality, and achieves notable computational efficiency through the coarse-to-fine strategy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12474 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Co-Layout: LLM-driven Co-optimization for Interior Layout Xiang, Chucheng Bao, Ruchao Feng, Biyin Wu, Wenzheng Liu, Zhongyuan Guan, Yirui Liu, Ligang Computer Vision and Pattern Recognition Computation and Language Graphics We present a novel framework for automated interior design that combines large language models (LLMs) with grid-based integer programming to jointly optimize room layout and furniture placement. Given a textual prompt, the LLM-driven agent workflow extracts structured design constraints related to room configurations and furniture arrangements. These constraints are encoded into a unified grid-based representation inspired by ``Modulor". Our formulation accounts for key design requirements, including corridor connectivity, room accessibility, spatial exclusivity, and user-specified preferences. To improve computational efficiency, we adopt a coarse-to-fine optimization strategy that begins with a low-resolution grid to solve a simplified problem and guides the solution at the full resolution. Experimental results across diverse scenarios demonstrate that our joint optimization approach significantly outperforms existing two-stage design pipelines in solution quality, and achieves notable computational efficiency through the coarse-to-fine strategy. |
| title | Co-Layout: LLM-driven Co-optimization for Interior Layout |
| topic | Computer Vision and Pattern Recognition Computation and Language Graphics |
| url | https://arxiv.org/abs/2511.12474 |