Structured reconstruction is a non-trivial dense prediction problem, which extracts structural information (\eg, building corners and edges) from a raster image, then reconstructs it to a 2D planar graph accordingly. Compared with common segmentation or detection problems, it significantly relays on the capability that leveraging holistic geometric information for structural reasoning. Current transformer-based approaches tackle this challenging problem in a two-stage manner, which detect corners in the first model and classify the proposed edges (corner-pairs) in the second model. However, they separate two-stage into different models and only share the backbone encoder. Unlike the existing modeling strategies, we present an enhanced corner representation method: 1) It fuses knowledge between the corner detection and edge prediction by sharing feature in different granularity; 2) Corner candidates are proposed in four heatmap channels w.r.t its direction. Both qualitative and quantitative evaluations demonstrate that our proposed method can better reconstruct fine-grained structures, such as adjacent corners and tiny edges. Consequently, it outperforms the state-of-the-art model by +1.9\%@F-1 on Corner and +3.0\%@F-1 on Edge.

翻译：结构化重建是一项非平凡的密集预测问题，其从栅格图像中提取结构信息（如建筑角点和边缘），并据此重建为二维平面图。与常见的分割或检测问题相比，它显著依赖于利用整体几何信息进行结构推理的能力。当前基于Transformer的方法以两阶段方式处理这一挑战性问题：第一阶段检测角点，第二阶段对提出的边缘（角点对）进行分类。然而，它们将两阶段分离至不同模型，仅共享主干编码器。与现有建模策略不同，我们提出一种增强的角点表征方法：1) 通过共享不同粒度的特征，在角点检测与边缘预测之间融合知识；2) 角点候选按方向在四个热力通道中提出。定性与定量评估均表明，我们的方法能更好重建细粒度结构，如相邻角点与微小边缘。最终，其在角点F-1指标上超越现有最佳模型+1.9%，在边缘F-1指标上超越+3.0%。