Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Li, K., Zhou, Z., Li, Z., Shan, H., Chen, Z., Deng, Y., Xi, Z., Meng, Y., Peng, Y., & Zhao, X. (2026). LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery. https://omanscience.com/en/articles/lodeot-low-dimensional-and-efficient-offset-tokens-for-building-footprint-extraction-from-off-nadir-imagery
MLA 9
Li, Kai, et al. "LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery." https://omanscience.com/en/articles/lodeot-low-dimensional-and-efficient-offset-tokens-for-building-footprint-extraction-from-off-nadir-imagery.
Chicago (author–date)
Li, Kai, Zigan Zhou, Zhenyang Li, Hui Shan, Zhe Chen, Yupeng Deng, Zhihao Xi, Yu Meng, Yifan Peng, and Xiangyu Zhao. 2026. "LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery." https://omanscience.com/en/articles/lodeot-low-dimensional-and-efficient-offset-tokens-for-building-footprint-extraction-from-off-nadir-imagery.
Harvard
Li, K., Zhou, Z., Li, Z., Shan, H., Chen, Z., Deng, Y., Xi, Z., Meng, Y., Peng, Y. and Zhao, X. (2026) 'LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery', Available at: https://omanscience.com/en/articles/lodeot-low-dimensional-and-efficient-offset-tokens-for-building-footprint-extraction-from-off-nadir-imagery.
Vancouver
Li K, Zhou Z, Li Z, Shan H, Chen Z, Deng Y, et al. LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery. https://omanscience.com/en/articles/lodeot-low-dimensional-and-efficient-offset-tokens-for-building-footprint-extraction-from-off-nadir-imagery
IEEE
K. Li, Z. Zhou, Z. Li, H. Shan, Z. Chen, Y. Deng, Z. Xi, Y. Meng, Y. Peng, and X. Zhao, "LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery," https://omanscience.com/en/articles/lodeot-low-dimensional-and-efficient-offset-tokens-for-building-footprint-extraction-from-off-nadir-imagery.