比较两种地板图矢量化输出方式，发现检测优于生成，但规模影响结果。
When Should a Network Emit Geometry, and When Should It Detect It? Readout, Reconciliation, and Representation in Floorplan Vectorization
- 用热图检测几何比自回归序列生成更准
- 真实扫描中检测提升2.7~5.1点墙识别率
- 大图用检测，小图用生成，融合可提效7点
训练网络恢复栅格化地板图的墙体、开口和房间时，可选择自回归坐标序列输出或基于密集角点与中心线热图的检测组装图结构。在真实扫描数据集CubiCasa5K上，检测方式在所有墙体指标上均更优（容忍度0.05时+2.7，0.015时+5.1；配对bootstrap区间不包含零）；仅读取解码器未使用的开口热图即可使开口F1提升2.6倍而无需重训练。真实数据中，读出方式优势随平面尺寸增大而增强，小平面则逆转；在干净矢量渲染上，序列解码领先5~8点，当训练覆盖渲染风格时；全域偏移下，校准阈值后检测仍占优；墨水密度和平面大小无法解释该反转。在相同数据和流程下，以房间为中心并含校正步骤的系统与墙体优先的序列模型达到相近墙体质量，说明输出表示的影响小于通常认知。来自另一类别的先验仅在输出端有效：两输出确定性融合使墙F1提升7点，而以对方输出为条件的三种形式（包括两个真值内容控制）均无增益。本文还提供编辑成本度量，评估修正草稿所需人工工作量，并发布经修正标注的CubiCasa5K与ResPlan-FP（16,998个计划，含冻结划分和三基准赛道），代码、基准与修正标注见https://github.com/Cyprinus12138/fpvec-lab。
原文摘要 · Abstract (English)
A network trained to recover the walls, openings, and rooms of a rasterized floorplan can produce its output in two ways: by emitting the geometry as an autoregressive coordinate sequence, or by detecting it on dense junction and centerline heatmaps and assembling a graph. We compare the two readouts on the same trained network. On real scans (CubiCasa5K) detection is better on every wall measure (+2.7 wall F1 at tolerance 0.05, +5.1 at 0.015; paired bootstrap intervals exclude zero), and reading an opening heatmap the decoder never used raises opening F1 by 2.6x without retraining. Within real scans the readout's advantage grows with plan size and reverses on small plans; on clean vector renders sequence decoding is better by 5 to 8 points where its training covered the render style, while under full domain shift the readout, given calibrated thresholds, stays ahead; neither ink density nor plan size explains the reversal. With matched data and recipe, a room-centric system with a reconciliation step and a wall-first sequence model reach comparable wall quality, so the output representation matters less than is usually assumed. A prior from the other family helps at the output but not at the input: deterministic fusion of the two outputs raises wall F1 by 7 points, whereas conditioning one model on the other's output gives no gain in three forms, including two ground-truth-content controls. We also provide an edit-cost metric that scores a draft by the human work needed to correct it, corrected CubiCasa5K annotations, and ResPlan-FP, a CC BY 4.0 benchmark of 16,998 plans with frozen splits and three baseline tracks. Code, the benchmark, and the corrected annotations are available at https://github.com/Cyprinus12138/fpvec-lab
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。