Monocular depth estimation works well on lunar terrain images
Efficacy of Monocular Depth Estimation in Lunar Environments
RoboticsComputer Vision and Pattern Recognition
Summary
Getting a sense of depth from just one camera image is a tough challenge, especially on the moon where conditions are very different from Earth. This paper looks at how well modern computer techniques for estimating depth work when applied to pictures of the moon's surface. The authors tested different methods using special Earth-based lunar-like images and real Apollo 17 photos. They found that some methods can still create good 3D maps of the moon’s uneven surface, even though these tools were mostly trained on Earth scenes.
What this means in practice
- •For planetary rover developers: Use monocular depth estimation to generate real-time 3D maps of lunar terrain for navigation aids where stereo cameras are limited.
- •For virtual reality content creators: Create accurate 3D models of the moon’s surface from single images for immersive educational or entertainment experiences.$Commercial implications: Enables production of commercial lunar VR environments using fewer sensors, reducing complexity and cost.
Authors
Michael W. Lanighan, Kenji Brameld, Seth Gee
Abstract
Recent advances in monocular depth estimation have demonstrated highly accurate 3D reconstructions within in-distribution terrestrial domains. This study investigates the efficacy of several state-of-the-art approaches to reconstruct out-of-distribution lunar environments using the NASA Ames Polar Optical Lunar Analog Reconstruction (POLAR) stereo dataset and Apollo 17 surface imagery. By leveraging these datasets, we establish a robust analog-to-field validation pipeline that evaluates quantitative performance against ground-truth physical analogs and qualitative performance against historical field data. Our results indicate that select state-of-the-art techniques can successfully generalize to produce high-fidelity relative 3D reconstructions of the unstructured lunar surface.