AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
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_ | 1866913929506062336 |
|---|---|
| author | Chen, Weixing Chi, Dafeng Liu, Yang Yang, Yuxi Zhang, Yexin Zhuang, Yuzheng Quan, Xingyue Hao, Jianye Li, Guanbin Lin, Liang |
| author_facet | Chen, Weixing Chi, Dafeng Liu, Yang Yang, Yuxi Zhang, Yexin Zhuang, Yuzheng Quan, Xingyue Hao, Jianye Li, Guanbin Lin, Liang |
| contents | The automated generation of layouts is vital for embodied intelligence and autonomous systems, supporting applications from virtual environment construction to home robot deployment. Current approaches, however, suffer from spatial hallucination and struggle with balancing semantic fidelity and physical plausibility, often producing layouts with deficits such as floating or overlapping objects and misaligned stacking relation. In this paper, we propose AutoLayout, a fully automated method that integrates a closed-loop self-validation process within a dual-system framework. Specifically, a slow system harnesses detailed reasoning with a Reasoning-Reflection-Generation (RRG) pipeline to extract object attributes and spatial constraints. Then, a fast system generates discrete coordinate sets and a topological relation set that are jointly validated. To mitigate the limitations of handcrafted rules, we further introduce an LLM-based Adaptive Relation Library (ARL) for generating and evaluating layouts. Through the implementation of Slow-Fast Collaborative Reasoning, the AutoLayout efficiently generates layouts after thorough deliberation, effectively mitigating spatial hallucination. Its self-validation mechanism establishes a closed-loop process that iteratively corrects potential errors, achieving a balance between physical stability and semantic consistency. The effectiveness of AutoLayout was validated across 8 distinct scenarios, where it demonstrated a significant 10.1% improvement over SOTA methods in terms of physical plausibility, semantic consistency, and functional completeness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning Chen, Weixing Chi, Dafeng Liu, Yang Yang, Yuxi Zhang, Yexin Zhuang, Yuzheng Quan, Xingyue Hao, Jianye Li, Guanbin Lin, Liang Robotics Computer Vision and Pattern Recognition The automated generation of layouts is vital for embodied intelligence and autonomous systems, supporting applications from virtual environment construction to home robot deployment. Current approaches, however, suffer from spatial hallucination and struggle with balancing semantic fidelity and physical plausibility, often producing layouts with deficits such as floating or overlapping objects and misaligned stacking relation. In this paper, we propose AutoLayout, a fully automated method that integrates a closed-loop self-validation process within a dual-system framework. Specifically, a slow system harnesses detailed reasoning with a Reasoning-Reflection-Generation (RRG) pipeline to extract object attributes and spatial constraints. Then, a fast system generates discrete coordinate sets and a topological relation set that are jointly validated. To mitigate the limitations of handcrafted rules, we further introduce an LLM-based Adaptive Relation Library (ARL) for generating and evaluating layouts. Through the implementation of Slow-Fast Collaborative Reasoning, the AutoLayout efficiently generates layouts after thorough deliberation, effectively mitigating spatial hallucination. Its self-validation mechanism establishes a closed-loop process that iteratively corrects potential errors, achieving a balance between physical stability and semantic consistency. The effectiveness of AutoLayout was validated across 8 distinct scenarios, where it demonstrated a significant 10.1% improvement over SOTA methods in terms of physical plausibility, semantic consistency, and functional completeness. |
| title | AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.04293 |