Deep Learning Eliminates Massive Dust Storms from Images of Tianwen-1
This addresses the issue of delayed global mapping for Martian exploration, but it is incremental as it adapts existing methods to a new domain.
The paper tackled the problem of dust storms degrading Martian orbiter images by reusing Earth-based dehazing knowledge to train a deep model, resulting in effectively eliminated dust storms and improved topographical details.
Dust storms may remarkably degrade the imaging quality of Martian orbiters and delay the progress of mapping the global topography and geomorphology. To address this issue, this paper presents an approach that reuses the image dehazing knowledge obtained on Earth to resolve the dust-removal problem on Mars. In this approach, we collect remote-sensing images captured by Tianwen-1 and manually select hundreds of clean and dusty images. Inspired by the haze formation process on Earth, we formulate a similar visual degradation process on clean images and synthesize dusty images sharing a similar feature distribution with realistic dusty images. These realistic clean and synthetic dusty image pairs are used to train a deep model that inherently encodes dust irrelevant features and decodes them into dust-free images. Qualitative and quantitative results show that dust storms can be effectively eliminated by the proposed approach, leading to obviously improved topographical and geomorphological details of Mars.