We address 2D floorplan reconstruction from 3D scans. Existing approaches typically employ heuristically designed multi-stage pipelines. Instead, we formulate floorplan reconstruction as a single-stage structured prediction task: find a variable-size set of polygons, which in turn are variable-length sequences of ordered vertices. To solve it we develop a novel Transformer architecture that generates polygons of multiple rooms in parallel, in a holistic manner without hand-crafted intermediate stages. The model features two-level queries for polygons and corners, and includes polygon matching to make the network end-to-end trainable. Our method achieves a new state-of-the-art for two challenging datasets, Structured3D and SceneCAD, along with significantly faster inference than previous methods. Moreover, it can readily be extended to predict additional information, i.e., semantic room types and architectural elements like doors and windows. Our code and models will be available at: https://github.com/ywyue/RoomFormer.
翻译:我们从 3D 扫描 中处理 2D 的二维楼层规划重建。 现有方法通常使用超常设计的多级管道。 相反, 我们制定楼层规划重建作为单阶段结构化的预测任务: 找到一套可变规模的多边形图, 后者反过来是定序脊椎的变长序列。 为了解决这个问题, 我们开发了一个新型的变形器结构, 以整体的方式生成多个房间的多元形, 不带手工制作的中间级。 模型中含有对多边形和角的双级查询, 并包含使网络端到端可训练的多级匹配。 我们的方法在两个挑战性数据集( 结构化3D 和 SceneceCDD) 和 ScenecAD 上取得了新的艺术状态, 并且比以前的方法要快得多。 此外, 它可以随时扩展, 以预测额外的信息, 例如, 语系室类型和建筑元素元素, 如门窗。 我们的代码和模型将可以在 https://github.com/ywyue/Romformermer 上提供 。