Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Rendering

TL;DR

This paper introduces neural terrain maps (NTM), a novel neural volume rendering approach that directly learns textured digital terrain maps from satellite imagery without requiring depth or structural priors, improving DTM generation for planetary exploration.

Contribution

The work adapts neural volume rendering to create high-quality DTMs directly from satellite images, eliminating the need for manual preprocessing and structural priors, and demonstrating effectiveness on Earth and Mars data.

Findings

Achieves terrain prediction accuracy nearly equal to satellite image resolution.

Works effectively with imperfect camera parameters.

Demonstrates on large-scale synthetic and real satellite datasets.

Abstract

Digital terrain maps (DTMs) are an important part of planetary exploration, enabling operations such as terrain relative navigation during entry, descent, and landing for spacecraft and aiding in navigation on the ground. As robotic exploration missions become more ambitious, the need for high quality DTMs will only increase. However, producing DTMs via multi-view stereo pipelines for satellite imagery, the current state-of-the-art, can be cumbersome and require significant manual image preprocessing to produce satisfactory results. In this work, we seek to address these shortcomings by adapting neural volume rendering techniques to learn textured digital terrain maps directly from satellite imagery. Our method, neural terrain maps (NTM), only requires the locus for each image pixel and does not rely on depth or any other structural priors. We demonstrate our method on both synthetic and real satellite data from Earth and Mars encompassing scenes on the order of $100 \textrm{km}^2$. We evaluate the accuracy of our output terrain maps by comparing with existing high-quality DTMs produced using traditional multi-view stereo pipelines. Our method shows promising results, with the precision of terrain prediction almost equal to the resolution of the satellite images even in the presence of imperfect camera intrinsics and extrinsics.