SU-ESRGAN: Semantic and Uncertainty-Aware ESRGAN for Super-Resolution of Satellite and Drone Imagery with Fine-Tuning for Cross Domain Evaluation
This work addresses the need for reliable super-resolution in critical remote sensing tasks such as disaster response and urban planning, though it is incremental as it builds on existing ESRGAN with added modules.
The paper tackles super-resolution for satellite and drone imagery by introducing SU-ESRGAN, which integrates semantic segmentation and uncertainty estimation to improve credibility in remote sensing applications, achieving results comparable to Baseline ESRGAN on metrics like PSNR, SSIM, and LPIPS.
Generative Adversarial Networks (GANs) have achieved realistic super-resolution (SR) of images however, they lack semantic consistency and per-pixel confidence, limiting their credibility in critical remote sensing applications such as disaster response, urban planning and agriculture. This paper introduces Semantic and Uncertainty-Aware ESRGAN (SU-ESRGAN), the first SR framework designed for satellite imagery to integrate the ESRGAN, segmentation loss via DeepLabv3 for class detail preservation and Monte Carlo dropout to produce pixel-wise uncertainty maps. The SU-ESRGAN produces results (PSNR, SSIM, LPIPS) comparable to the Baseline ESRGAN on aerial imagery. This novel model is valuable in satellite systems or UAVs that use wide field-of-view (FoV) cameras, trading off spatial resolution for coverage. The modular design allows integration in UAV data pipelines for on-board or post-processing SR to enhance imagery resulting due to motion blur, compression and sensor limitations. Further, the model is fine-tuned to evaluate its performance on cross domain applications. The tests are conducted on two drone based datasets which differ in altitude and imaging perspective. Performance evaluation of the fine-tuned models show a stronger adaptation to the Aerial Maritime Drone Dataset, whose imaging characteristics align with the training data, highlighting the importance of domain-aware training in SR-applications.