ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields

TL;DR

ImpliCity introduces a neural implicit occupancy field approach for 3D city modeling from satellite images, significantly improving detail and accuracy over traditional methods by leveraging learned embeddings from point clouds and stereo images.

Contribution

The paper presents ImpliCity, a novel neural implicit representation that enhances 3D city reconstruction quality from satellite data by utilizing learned embeddings and continuous occupancy fields.

Findings

Median height error of approximately 0.7 meters at 0.5m resolution

Outperforms existing methods in building detail reconstruction

Effectively captures intricate roof details and regular outlines

Abstract

High-resolution optical satellite sensors, combined with dense stereo algorithms, have made it possible to reconstruct 3D city models from space. However, these models are, in practice, rather noisy and tend to miss small geometric features that are clearly visible in the images. We argue that one reason for the limited quality may be a too early, heuristic reduction of the triangulated 3D point cloud to an explicit height field or surface mesh. To make full use of the point cloud and the underlying images, we introduce ImpliCity, a neural representation of the 3D scene as an implicit, continuous occupancy field, driven by learned embeddings of the point cloud and a stereo pair of ortho-photos. We show that this representation enables the extraction of high-quality DSMs: with image resolution 0.5$\,$m, ImpliCity reaches a median height error of $\approx\,$0.7$\,$m and outperforms competing methods, especially w.r.t. building reconstruction, featuring intricate roof details, smooth surfaces, and straight, regular outlines.