Abstract
Digital surface model generation using traditional multi-view stereo matching (MVS) performs poorly over non-Lambertian surfaces, with asynchronous acquisitions, or at discontinuities. Neural radiance fields (NeRF) offer a new paradigm for reconstructing surface geometries using continuous volumetric representation. NeRF is self-supervised, does not require ground truth geometry for training, and provides an elegant way to include in its representation physical parameters about the scene, thus potentially remedying the challenging scenarios where MVS fails. However, NeRF and its variants require many views to produce convincing scene's geometries which in earth observation satellite imaging is rare. In this paper we present SparseSat-NeRF (SpS-NeRF) - an extension of Sat-NeRF adapted to sparse satellite views. SpS-NeRF employs dense depth supervision guided by crosscorrelation similarity metric provided by traditional semi-global MVS matching. We demonstrate the effectiveness of our approach on stereo and tri-stereo Pleiades 1B/WorldView-3 images, and compare against NeRF and Sat-NeRF. The code is available at this https URL
Abstract (translated)
使用传统的多视图三角测量(MVS)方法生成数字表面模型在非Lambertian表面、 asynchronous acquisition 或中断处表现不佳。神经光辐射场(NeRF)提供了使用连续体积表示重构表面几何学的新范式。 NeRF是自我监督的,不需要 ground truth 几何学进行训练,并提供了一种优雅的方式,将其表示的物理参数包括在它的表示中,从而可能修复在 MVS 失败时的 challenging 场景。然而, NeRF 及其变体需要许多视图才能产生有说服力的场景几何学,这在地球观测卫星图像中是非常罕见的。在本文中,我们介绍了稀疏卫星-NeRF(SpS-NeRF) - Sat-NeRF 的扩展,以适应稀疏卫星视图。 SpS-NeRF采用Dense depth supervision,受传统半全局MVS匹配提供的交叉相关相似度度量的指导。我们证明了我们的方法在三角和三角多视图 Pleiades 1B/WorldView-3 图像中的 effectiveness,并对比了 NeRF 和Sat-NeRF。代码在此https URL 可用。
URL
https://arxiv.org/abs/2309.00277