布局万物：一种用于通用房间布局估计的变换器
Layout Anything: One Transformer for Universal Room Layout Estimation
- Nanjing University of Information Science and Technology（南京信息工程大学）
- Bangladesh University of Engineering and Technology（孟加拉国工程与技术大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Layout Anything通过整合任务条件查询和对比学习，提出了一种基于变换器的通用房间布局估计框架，实现了高速推理和高精度性能。
AI中文摘要：
我们提出了Layout Anything，一种基于变换器的框架，用于室内布局估计，该框架将OneFormer的通用分割架构适应到几何结构预测。我们的方法整合了OneFormer的任务条件查询和对比学习，与两个关键模块：（1）一种布局退化策略，通过拓扑感知变换在增强训练数据的同时保持曼哈顿世界约束，以及（2）可微的几何损失，直接在训练过程中强制平面一致性和清晰边界预测。通过在端到端框架中统一这些组件，模型消除了复杂的后处理流程，同时在114毫秒内实现高速推理。广泛的实验表明，该方法在标准基准上实现了最先进的性能，其在LSUN上的像素误差（PE）为5.43%，角误差（CE）为4.02%；在Hedau上的PE为7.04%（CE 5.17%）；在Matterport3D-Layout数据集上的PE为4.03%（CE 3.15%）。该框架结合了几何意识和计算效率，使其特别适用于增强现实应用和大规模3D场景重建任务。
英文摘要：
We present Layout Anything, a transformer-based framework for indoor layout estimation that adapts the OneFormer's universal segmentation architecture to geometric structure prediction. Our approach integrates OneFormer's task-conditioned queries and contrastive learning with two key modules: (1) a layout degeneration strategy that augments training data while preserving Manhattan-world constraints through topology-aware transformations, and (2) differentiable geometric losses that directly enforce planar consistency and sharp boundary predictions during training. By unifying these components in an end-to-end framework, the model eliminates complex post-processing pipelines while achieving high-speed inference at 114ms. Extensive experiments demonstrate state-of-the-art performance across standard benchmarks, with pixel error (PE) of 5.43% and corner error (CE) of 4.02% on the LSUN, PE of 7.04% (CE 5.17%) on the Hedau and PE of 4.03% (CE 3.15%) on the Matterport3D-Layout datasets. The framework's combination of geometric awareness and computational efficiency makes it particularly suitable for augmented reality applications and large-scale 3D scene reconstruction tasks.
