What question did this study set out to answer?

This research aims to develop a novel GAN that enhances the generation of high-resolution Martian DTMs by integrating physical knowledge.

May 1, 2026Open Access

PFMGAN: A Generative Adversarial Network with Physics Fusion for DTM Generation from Martian Monocular Images

Key Points

This research aims to develop a novel GAN that enhances the generation of high-resolution Martian DTMs by integrating physical knowledge.
Developed a Physics Fusion GAN based on the Mix Transformer architecture that uses physical prior knowledge.
Incorporated an Albedo-Aware Attention (AAA) module to address grayscale variations caused by surface albedo and terrain undulations.
Evaluated the model's performance across various Martian landforms and spatial scales.
PFMGAN achieved a 50% improvement in reconstruction accuracy in complex terrains compared to baseline models.
Results indicated the model's adaptability, consistently delivering high-quality topographic products across multi-scale (0.25–6 m/pixel) tasks.
The experimental results underscore PFMGAN's potential for large-scale Martian terrain reconstruction.

Abstract

High-resolution digital terrain models (DTMs) are essential for Martian scientific exploration and engineering missions. However, traditional methods for Martian DTM generation are constrained by limitations in coverage and production efficiency, while the implicit treatment of illumination in existing deep learning methods leads to reconstructions lacking physical interpretability. To address this, we propose a Physics Fusion generative adversarial network based on the Mix Transformer architecture (PFMGAN) that incorporates physical prior knowledge to reconstruct high-precision DTMs from monocular images. This design significantly improves the accuracy and robustness of DTMs by enabling the network to effectively interpret grayscale variations caused by surface albedo and terrain undulations. Experimental results across various Martian landforms demonstrate that, by explicitly inputting solar angles and leveraging an Albedo-Aware Attention (AAA) module, PFMGAN achieves superior accuracy and robustness compared to other baseline models, with up to a 50% improvement in reconstruction accuracy in complex terrains. Furthermore, multi-scale (0.25–6 m/pixel) experimental results indicate that the proposed model is highly adaptable to reconstruction tasks across different spatial scales, consistently delivering high-quality topographic products. The results demonstrate the immense potential of PFMGAN for large-scale, high-precision Martian terrain reconstruction by leveraging the vast archive of monocular imagery.

Read Full Paperexternally

AI에게 질문

Bookmark

View Full Paper