Improving Lunar Topography with Deep Learning Schrödinger Bridges
2026-06-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method to improve the detail of moon surface maps by turning low-resolution data into high-resolution images using a special type of AI called diffusion-based Schrödinger Bridge models. Their approach also uses pictures taken from a lunar camera to help guide the improvement, similar to how previous methods used light and shadow to refine surface shapes. They trained their model on a dataset designed to mimic real lunar images. This method can efficiently create better moon maps and also tells how confident it is about each part of the improved image.
planetary topographysuper-resolutiondiffusion modelsSchrödinger BridgeShape-from-ShadingLunar Reconnaissance Orbiteroptical imagerygenerative modelinguncertainty quantification
Authors
Matthew Repasky, Erwan Mazarico, Michael K. Barker, Stefano Bertone, Terence J. Sabaka, Yao Xie
Abstract
Increasing the resolution of planetary topography models can enable a better understanding of surface processes and geomorphology; however, existing analytical super-resolution methods are expensive and difficult to apply at large scales. Generative models provide the tools to learn complex relationships within data and can be applied at scale due to hardware accelerators and parallelization. We present a diffusion-based Schrödinger Bridge (SB) generative modeling approach for lunar topography super-resolution, connecting the distribution of low-resolution topography to that of high-resolution topography, incorporating physically-constraining optical imagery. Our approach is inspired by existing Shape-from-Shading methods, which improve a priori low-resolution topography by using optical images at the target resolution. We train SBs on a novel dataset of rendered lunar topography, emulating optical imagery from the Lunar Reconnaissance Orbiter Narrow Angle Camera. The result is a flexible approach for topography super-resolution which can provide pixel-level uncertainties in the reconstruction.