构建真实建筑3D布局基准，无需训练即可超越现有模型。
HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild
- 提出多层建筑3D布局估计的无训练基线方法
- 在真实数据上优于已有模型，尤其擅长处理多层结构
- 适合关注真实场景、跨楼层推理的研究者
当前3D布局估计模型主要基于合成数据集训练，仅适用于简单单层房间环境。因此无法直接处理大型多层建筑，需将场景拆分为单层处理，丢失了楼梯等连接多层结构所需的整体空间上下文。本文提出HouseLayout3D，一个面向真实世界多层建筑的3D布局估计基准，支持全建筑尺度的布局推断，涵盖复杂建筑结构。同时引入MultiFloor3D，一种无需训练的基线方法，利用现有场景理解技术，在本基准及以往数据集上均表现优于现有模型，凸显该方向仍有巨大研究空间。数据与代码已公开：https://houselayout3d.github.io。
原文摘要 · Abstract (English)
Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be split into individual floors before processing, which removes global spatial context that is essential for reasoning about structures such as staircases that connect multiple levels. In this work, we introduce HouseLayout3D, a real world benchmark designed to support progress toward full building scale layout estimation, including multiple floors and architecturally intricate spaces. We also present MultiFloor3D, a simple training free baseline that leverages recent scene understanding methods and already outperforms existing 3D layout estimation models on both our benchmark and prior datasets, highlighting the need for further research in this direction. Data and code are available at: https://houselayout3d.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。