Depth Supervised Neural Surface Reconstruction from Airborne Imagery

TL;DR

This paper explores the use of depth-supervised NeRFs, specifically VolSDF, for aerial surface reconstruction from airborne imagery, demonstrating the benefits of integrating depth priors in challenging scenarios like street canyons.

Contribution

It investigates the applicability of NeRFs for airborne imagery and introduces the integration of depth priors from tie-point measures during reconstruction.

Findings

NeRFs can be effectively applied to aerial imagery with different characteristics.

Depth priors improve reconstruction quality in low redundancy areas.

The approach outperforms traditional methods on benchmark datasets.

Abstract

While originally developed for novel view synthesis, Neural Radiance Fields (NeRFs) have recently emerged as an alternative to multi-view stereo (MVS). Triggered by a manifold of research activities, promising results have been gained especially for texture-less, transparent, and reflecting surfaces, while such scenarios remain challenging for traditional MVS-based approaches. However, most of these investigations focus on close-range scenarios, with studies for airborne scenarios still missing. For this task, NeRFs face potential difficulties at areas of low image redundancy and weak data evidence, as often found in street canyons, facades or building shadows. Furthermore, training such networks is computationally expensive. Thus, the aim of our work is twofold: First, we investigate the applicability of NeRFs for aerial image blocks representing different characteristics like nadir-only, oblique and high-resolution imagery. Second, during these investigations we demonstrate the benefit of integrating depth priors from tie-point measures, which are provided during presupposed Bundle Block Adjustment. Our work is based on the state-of-the-art framework VolSDF, which models 3D scenes by signed distance functions (SDFs), since this is more applicable for surface reconstruction compared to the standard volumetric representation in vanilla NeRFs. For evaluation, the NeRF-based reconstructions are compared to results of a publicly available benchmark dataset for airborne images.