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

TL;DR

This paper presents a novel dual-topology neural network framework that converts noisy spaceborne TomoSAR point clouds into accurate, high-resolution urban building height maps, effectively addressing data noise, voids, and anisotropy.

Contribution

The paper introduces the first large-scale urban height mapping method directly from TomoSAR point clouds using a dual-topology network that denoises and inpaints data.

Findings

The approach accurately reconstructs building heights in Munich and Berlin.

The method outperforms traditional techniques in handling noise and data voids.

Incorporating optical imagery further improves height estimation quality.

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.