← Back to NASA Technology Projects
Completed TRL 3 (started at 1, targeting 3)
The Neural Radiance Methods project aims to revolutionize digital elevation model (DEM) reconstruction of the lunar surface by addressing the persistent challenge of shadowed regions. Current state-of-the-art methods, such as Structure-from-Motion and Shape-from-Shading, fail at reconstructing permanently shadowed regions (PSRs) on the Moon due the harsh shading and diffusive reflection. Neural Radiance Fields (NeRFs) may address these limitations by employing neural networks to model both the light and geometry of a 3D scene. This project is developing a shadow-aware NeRF methods for high-fidelity reconstructions of lunar surface features, particularly in low-illumination areas, from existing Lunar Reconnaissance Orbiter Camera (LROC) and Lunar Orbital Laser Altimeter (LOLA) datasets. The project focuses on the lunar South Pole, a key target for the NASA Artemis campaign due to its potential for water ice deposits and future human exploration.
Neural Radiance Methods (NRMs) can reconstruct complex lighting conditions that occur in the space environment better than traditional methods by modeling the transmissive properties of light, removing shadows and reflective artifacts, and accounting for image noise during a 3D reconstruction. We use existing lunar imagery datasets to compare NRMs to standard Structure from Shading, Localization and Mapping, and Structure from Motion methods.
Anticipated benefits include:
1. Enhanced Lunar Surface Mapping – By incorporating shadow-aware methodologies and leveraging multi-sensor information, our method may significantly improve the accuracy of DEMs in shadowed regions, which are currently challenging to reconstruct with existing techniques.
2. Advanced Shadow Removal Capabilities – Our approach will enable the ability to dynamically relight and remove shadows from lunar surface models, allowing for the visualization of terrain features that were previously obscured. This capability will provide a clearer and more detailed understanding of the lunar surface.
3. Improved Mission Planning for Lunar Exploration – Accurate terrain reconstructions will aid in the selection of safe landing sites and navigation paths for future lunar missions, particularly those targeting the South Pole.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.
None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.