MARTIAN: A Rendering Framework for Aerial Mars Imagery from HiRISE Orbital Data

2026-05-28

AI Summary

This study addresses the scarcity of large-scale, annotated real aerial imagery for Mars visual navigation, which has hindered algorithm training and evaluation. To bridge this gap, the authors present an open-source Blender-based rendering framework built upon HiRISE orbital maps, enabling, for the first time, the generation of photorealistic synthetic aerial images grounded in actual Martian terrain. The framework supports controllable variations in illumination conditions and flight altitudes and provides precise pose annotations. This approach effectively fills the critical void in training data for Mars visual navigation. The generated dataset has already been successfully integrated into the map-based localization systems of the Ingenuity helicopter and future rotorcraft missions. Experimental validation demonstrates that deep image-matching models trained solely on this synthetic data exhibit strong performance on real Mars imagery.

Abstract

Aerial navigation on Mars requires vision-based pipelines that are robust to the diverse illumination conditions and terrain morphology of the Martian surface. A key bottleneck for training and evaluating such methods is the scarcity of large-scale, annotated aerial datasets. We present MARTIAN, an open-source Blender-based rendering framework that leverages real HiRISE orbital map products to synthesize realistic aerial views of the Martian terrain under controllable lighting conditions and at varying altitudes. MARTIAN generates observations with accurate pose annotations, directly addressing the scarcity of training data for vision-based navigation on Mars. The framework has been validated through its deployment in concurrent work on map-based localization systems for Ingenuity and future Mars rotorcraft, where synthetically trained deep image matchers were successfully evaluated on real Mars imagery. MARTIAN is publicly available at: https://github.com/nasa-jpl/martian.

Problem

• Mars aerial navigation
• vision-based navigation
• annotated aerial datasets
• data scarcity
• Martian terrain

Innovation

• MARTIAN
• HiRISE
• synthetic data generation
• aerial navigation
• Mars terrain rendering