发表机构
City University of Hong Kong; University of the Chinese Academy of Sciences; University of Hong Kong; Zhejiang University; University of Southampton（香港城市大学; 中国科学院大学; 香港大学; 浙江大学; 南安普顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LoDEOT提出五维偏移令牌用于非天底影像建筑物轮廓提取，通过结构先验和端到端训练实现高效准确的RFO预测，在BONAI上取得领先性能。
AI 中文摘要
实例级屋顶到轮廓偏移（RFO）预测是从非天底影像中提取建筑物轮廓的核心。基于查询的流程通常使用高维实例令牌来预测带符号的二维RFO。我们研究RFO预测是否可以使用紧凑的偏移令牌。在局部针孔投影和垂直拉伸假设下，理想化的RFO图具有一个五参数充分描述符，包含内在形状、复合幅度和相对几何。这种分解为五维偏移令牌提供了结构先验，其通道通过端到端训练学习任务相关的潜在表示。基于此设计，我们提出LoDEOT，它保留高维实例令牌用于检测和分割，但将实例令牌、浓度门控屋顶和框掩码证据映射到五维偏移令牌，随后进行独立的二维读出。已知的去噪查询目标索引进一步将每个监督解码器层的估计与相同的干净实例RFO对齐，将连续预测组织为在扰动查询条件下的目标对齐恢复。在五个真实世界建筑物数据集上的实验证明了LoDEOT在建筑物轮廓提取中的有效性。在真实世界建筑物数据集上的实验表明，五维偏移令牌可以支持准确的RFO预测。在BONAI上，LoDEOT实现了最佳的屋顶检测bAP和bAP50，并在评估的端到端方法中领先所有五个偏移校正轮廓指标，FAP50为54.58，mEPE为5.23像素。其FAP50超过评估的端到端基线7.56-16.85个百分点。
英文摘要
Instance-level roof-to-footprint offset (RFO) prediction is central to extracting building footprints from off-nadir imagery. Query-based pipelines commonly use high-dimensional instance tokens to predict signed two-dimensional RFOs. We investigate whether RFO prediction can instead use a compact offset token. Under local pinhole projection and vertical-extrusion assumptions, the idealized RFO map admits a five-parameter sufficient descriptor comprising intrinsic shape, composite amplitude, and relative geometry. This factorization provides a structural prior for a five-dimensional offset token, whose channels learn task-relevant latent representations through end-to-end training. Based on this design, we propose LoDEOT, which retains high-dimensional instance tokens for detection and segmentation but maps instance-token, concentration-gated roof, and box-mask evidence to a five-dimensional offset token followed by an independent two-dimensional readout. Known denoising-query target indices further align each supervised decoder-layer estimate with the same clean instance RFO, organizing successive predictions as target-aligned recovery under perturbed query conditions. Experiments on five real-world building datasets demonstrate the effectiveness of LoDEOT for building footprint extraction. Experiments on real-world building datasets demonstrate that a five-dimensional offset token can support accurate RFO prediction. On BONAI, LoDEOT achieves the best roof-detection bAP and bAP50 and leads all five offset-corrected footprint metrics among the evaluated end-to-end methods, with FAP50 of 54.58 and mEPE of 5.23 pixels. Its FAP50 exceeds those of the evaluated end-to-end baselines by 7.56-16.85 percentage points.
Comments13 pages, 2 figures, 5 tables, including appendices
