用统一模型实现任意室内布局估计，速度快且精度高。
Layout Anything: One Transformer for Universal Room Layout Estimation
- 基于OneFormer架构，通过任务条件查询和对比学习预测几何结构
- 训练时引入拓扑感知增强与可微几何损失，提升平面一致性和边界清晰度
- 端到端输出，114毫秒高速推理，适合AR与大规模3D重建
我们提出Layout Anything，一个基于Transformer的室内布局估计框架，将OneFormer的通用分割架构拓展至几何结构预测。该方法结合任务条件查询与对比学习，并引入两个关键模块：(1) 布局退化策略，在保持曼哈顿世界约束的前提下，通过拓扑感知变换增强训练数据；(2) 可微几何损失，在训练中直接强制平面一致性与锐利边界预测。通过端到端整合，模型无需复杂后处理，实现114毫秒高速推理。大量实验表明，其在标准基准上表现领先：在LSUN上像素误差（PE）为5.43%，角点误差（CE）为4.02%；在Hedau上PE为7.04%（CE 5.17%）；在Matterport3D-Layout上PE为4.03%（CE 3.15%）。该框架兼具几何感知与计算高效性，特别适用于增强现实与大规模3D场景重建。
原文摘要 · Abstract (English)
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.
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。