SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images
This work addresses a domain-specific problem in earth observation for researchers and practitioners, offering an incremental improvement over existing NeRF adaptations for satellite imagery.
The paper tackles the problem of generating digital surface models from sparse satellite images, where traditional multi-view stereo matching fails and existing neural radiance field methods require many views. The result is SparseSat-NeRF, which uses dense depth supervision to improve geometry reconstruction, demonstrating effectiveness on stereo and tri-stereo satellite images with comparisons to NeRF and Sat-NeRF.
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 https://github.com/LulinZhang/SpS-NeRF