返回全部动态
LayoutDSL：在领域特定语言动作空间中学习室内布局策略
原标题：Learning an Interior Layout Policy in a Domain Specific Language Action Space
AI 摘要
arXiv 上发布了一篇关于室内布局生成的研究论文，提出了 LayoutDSL 框架，利用领域特定语言（DSL）作为动作空间，通过 LLM 学习布局策略。该方法将布局推理转化为可解释的设计决策，并构建了 3D-FrontDSL 数据集，结合强化学习优化策略。实验表明，LayoutDSL 在空间合理性和设计逻辑性上优于现有方法。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Computer Science > Computer Vision and Pattern Recognition Title:Learning an Interior Layout Policy in a Domain Specific Language Action Space View PDF HTML (experimental) Abstract:Indoor scene layout generation is a challenging task in interior design. Existing methods often oversimplify the task by reducing room conditions to coarse 3D bounding boxes and neglecting structural elements such as doors and windows. More fundamentally, many prior approaches formulate spatial reasoning a
发布时间：2026-08-11 12:00
抓取时间：2026-08-11 12:45
来源机构：arXiv