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.
Abstract (translated)
虽然最初是为 novel view synthesis 设计的，但近年来 Neural Radiance Fields (NeRFs) 已经作为一种多视图立体 (MVS) 的替代方案得到了广泛应用。受到多种研究活动的触发，尤其是在缺乏纹理、透明和反射表面的情况下，NeRFs 的表现尤为出色，而传统 MVS 方法在这些问题上仍然具有挑战性。然而，这些研究主要集中在近景场景，尽管已经对空气场景进行了研究，但仍有缺失。对于这项任务，NeRFs 在低图像冗余和弱数据证据的领域可能会面临潜在的困难，正如在街巷、建筑立面或建筑物阴影中常见的情况。此外，训练这类网络在计算上较为昂贵。因此，我们工作的目标是双重的：首先，我们研究 NeRFs 在代表不同特性的航空图像块上的适用性；其次，在這些調查期間，我們將展示將來自點測量學的深度 prior 整合到預假 Bundle Block Adjustment 中的好處。我们的工作基於最先进的框架 VolSDF，它通過點距函數 (SDF) 建模 3D 场景，因為這比標準的 NeRFs 的表面重建更適合作用。對於評估，我們將 NeRF 基於的重建與空氣中可獲得的公开數據集的結果進行比較。
URL
https://arxiv.org/abs/2404.16429
