Work

Cross-Task Mamba Network for Building Extraction and Height Estimation from Single-View Remote Sensing Images

Year: 2025

Type: article

Abstract: . Simultaneous building extraction and height estimation from single-view satellite imagery via multi-task learning presents a viable solution for large-scale urban 3D reconstruction. However, balancing the weights across different tasks and reducing conflicts between them remains a challenging problem. In this paper, we propose a Mamba-CNN based network to more effectively capture the spatial distribution of buildings. Additionally, we propose a cross-task feature fusion module to facilitate information exchange between tasks. Experiments conducted on the Vaihingen dataset demonstrate significant improvements achieved by the proposed method.

Source: The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences

DOI: 10.5194/isprs-archives-xlviii-4-w14-2025-61-2025

Authors: Yu He, Po Liu, Qingdong Wang, Nengcheng Chen, Liang Zhai

Institutions: China University of Geosciences, Chinese Academy of Surveying and Mapping

Language: English

Topic: Automated Road and Building Extraction

Subfield: Ocean Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Sustainable cities and communities

Open Access status: diamond

OpenAlex ID: W4416696344