Search papers, labs, and topics across Lattice.
This paper introduces a novel approach to correcting geometric projection displacements in oblique-view urban remote sensing imagery by explicitly defining roof-to-footprint offset vector (RFOV) extraction as a standalone learning task. The authors present the Oblique City dataset (ObliCity), a comprehensive benchmark that combines high-resolution UAV imagery with satellite data, enabling the evaluation of diverse urban structures and perspectives. Utilizing an ODE-based framework called DragRoof, the study achieves state-of-the-art performance in RFOV extraction with fewer inference steps and improved accuracy, thereby laying a solid foundation for future research in this area.
Achieving state-of-the-art RFOV extraction, DragRoof reduces inference steps while enhancing accuracy in correcting geometric displacements in urban imagery.
Oblique-view urban remote sensing imagery inevitably exhibits geometric projection displacements between building roofs and footprints, leading to significant distortions in spatial structure. Existing approaches either ignore these deformations or handle them implicitly within segmentation-based frameworks, where progress is dominated by general segmentation advances rather than improvements in geometric correction. In this work, we explicitly define roof-to-footprint offset vector (RFOV) extraction as an independent learning task that decouples geometric alignment from semantic segmentation. To support this task, we introduce the Oblique City dataset (ObliCity), the first large-scale benchmark that integrates high-resolution UAV imagery and globally distributed satellite data, covering diverse city morphologies and camera perspectives. Methodologically, we reformulate DragOSM into DragRoof, an ODE-based framework inspired by human annotation behavior. By simulating the continuous process of dragging roofs toward their footprints, DragRoof learns deterministic, geometry-consistent offset fields and adaptively determines convergence through an end token. Extensive experiments on ObliCity demonstrate that DragRoof achieves state-of-the-art RFOV extraction performance, requiring fewer inference steps while delivering superior directional and length accuracy. Our dataset and model establish a principled foundation for studying projection displacement correction in oblique remote sensing imagery. The source code and dataset will be avaliable at https://github.com/likaiucas/DragRoof.
