Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces MARTIAN, a Blender-based rendering framework that synthesizes realistic aerial views of Mars using HiRISE orbital map data. This framework addresses the scarcity of annotated aerial datasets for training vision-based navigation systems on Mars by generating images with accurate pose annotations and controllable lighting. The framework's utility is validated by successfully training deep image matchers on synthetic data and deploying them on real Mars imagery for map-based localization.
Training data no longer needs to be a bottleneck for Martian aerial navigation: MARTIAN generates realistic synthetic imagery from HiRISE data.
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.