让建筑立面分割更符合结构规律，提升重建可用性。
Beyond Segmentation: Structurally Informed Facade Parsing from Imperfect Images
- 用轻量级对齐损失增强YOLOv8，强制框体排列符合网格结构
- 在CMP数据集上显著减少透视与遮挡导致的错位问题
- 不改动推理流程，兼顾检测精度与结构合理性
标准目标检测器通常独立处理建筑元素，导致立面解析缺乏下游程序化重建所需的结构一致性。本文通过在YOLOv8训练目标中加入自定义轻量级对齐损失，使边界框在训练中保持网格一致排列，有效注入几何先验，且不改变标准推理流程。在CMP数据集上的实验表明，该方法能有效提升结构规整性，修正由透视和遮挡引起的对齐错误，同时维持检测精度与结构合理性的可控权衡。
原文摘要 · Abstract (English)
Standard object detectors typically treat architectural elements independently, often resulting in facade parsings that lack the structural coherence required for downstream procedural reconstruction. We address this limitation by augmenting the YOLOv8 training objective with a custom lightweight alignment loss. This regularization encourages grid-consistent arrangements of bounding boxes during training, effectively injecting geometric priors without altering the standard inference pipeline. Experiments on the CMP dataset demonstrate that our method successfully improves structural regularity, correcting alignment errors caused by perspective and occlusion while maintaining a controllable trade-off with standard detection accuracy.
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。