Radar Fields: An Extension of Radiance Fields to SAR
This work addresses the challenge of 3D modeling from SAR data for applications in remote sensing and imaging, representing an incremental extension of existing methods to a new modality.
The paper tackles the problem of extending radiance fields to synthetic aperture radar (SAR) images, presenting the first 'radar fields' that enable learning surface models from radar image collections with similar computational complexity as optical radiance fields.
Radiance fields have been a major breakthrough in the field of inverse rendering, novel view synthesis and 3D modeling of complex scenes from multi-view image collections. Since their introduction, it was shown that they could be extended to other modalities such as LiDAR, radio frequencies, X-ray or ultrasound. In this paper, we show that, despite the important difference between optical and synthetic aperture radar (SAR) image formation models, it is possible to extend radiance fields to radar images thus presenting the first "radar fields". This allows us to learn surface models using only collections of radar images, similar to how regular radiance fields are learned and with the same computational complexity on average. Thanks to similarities in how both fields are defined, this work also shows a potential for hybrid methods combining both optical and SAR images.