Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Network

2026-01-02

IEEE Transactions on Geoscience and Remote Sensing

AI Summary

This study addresses the challenge of reconstructing building heights from spaceborne TomoSAR point clouds, which are often degraded by noise, anisotropic point distributions, and data voids. To overcome these limitations, the authors propose a dual-topology deep learning network that alternately processes point-based and grid-based branches, jointly modeling irregular scattering characteristics while enforcing spatial consistency constraints to simultaneously denoise the point cloud and inpaint missing regions. This approach is the first to enable direct generation of large-scale, high-resolution urban building height maps from TomoSAR point clouds and further supports fusion with optical imagery to enhance reconstruction accuracy. Experiments on datasets from Munich and Berlin demonstrate that the method effectively produces continuous and highly accurate building height products.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Reliable building height estimation is essential for various urban applications. Spaceborne SAR tomography (TomoSAR) provides weather-independent, side-looking observations that capture facade-level structure, offering a promising alternative to conventional optical methods. However, TomoSAR point clouds often suffer from noise, anisotropic point distributions, and data voids on incoherent surfaces, all of which hinder accurate height reconstruction. To address these challenges, we introduce a learning-based framework for converting raw TomoSAR points into high-resolution building height maps. Our dual-topology network alternates between a point branch that models irregular scatterer features and a grid branch that enforces spatial consistency. By jointly processing these representations, the network denoises the input points and inpaints missing regions to produce continuous height estimates. To our knowledge, this is the first proof of concept for large-scale urban height mapping directly from TomoSAR point clouds. Extensive experiments on data from Munich and Berlin validate the effectiveness of our approach. Moreover, we demonstrate that our framework can be extended to incorporate optical satellite imagery, further enhancing reconstruction quality. The source code is available at https://github.com/zhu-xlab/tomosar2height.

Problem

• building height reconstruction
• TomoSAR point clouds
• data voids
• noise
• anisotropic point distribution

Innovation

• TomoSAR
• dual-topology network
• building height reconstruction
• point cloud denoising
• urban remote sensing