Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Rendering
This addresses the need for high-quality DTMs in planetary exploration, such as for spacecraft navigation, but is incremental as it adapts existing neural techniques to a specific domain.
The paper tackled the cumbersome and manual preprocessing required for producing digital terrain maps (DTMs) from satellite imagery by adapting neural volume rendering to learn textured DTMs directly from images, showing promising results with terrain prediction precision nearly matching satellite image resolution.
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.