# Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach Source: [Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach]() Collection index: [llms.txt]() Data updated: 2026-05-01T05:00:04.847Z Authors: Adrien Dorise, Marjorie Bellizzi, Omar Hlimi Published: 2026-04-14T14:37:26.000Z ## Abstract Satellite image restoration aims to improve image quality by compensating for degradations (e.g., noise and blur) introduced by the imaging system and acquisition conditions. As a fundamental preprocessing step, restoration directly impacts both ground-based product generation and emerging onboard AI applications. Traditional restoration pipelines based on sequential physical models are computationally intensive and slow, making them unsuitable for onboard environments. In this paper, we introduce ConvBEERS: a Convolutional Board-ready Embedded and Efficient Restoration model for Space to investigate whether a light and non-generative residual convolutional network, trained on simulated satellite data, can match or surpass a traditional ground-processing restoration pipeline across multiple operating conditions. Experiments conducted on simulated datasets and real Pleiades-HR imagery demonstrate that the proposed approach achieves competitive image quality, with a +6.9dB PSNR improvement. Evaluation on a downstream object detection task demonstrates that restoration significantly improves performance, with up to +5.1% mAP@50. In addition, successful deployment on a Xilinx Versal VCK190 FPGA validates its practical feasibility for satellite onboard processing, with a ~41x reduction in latency compared to the traditional pipeline. These results demonstrate the relevance of using lightweight CNNs to achieve competitive restoration quality while addressing real-world constraints in spaceborne systems. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Restoration on 13600 × 9016 panchromatic swath image (Versal AI Edge VCK190 FPGA) inference benchmark](): Image Restoration; 13600 × 9016 panchromatic swath image (Versal AI Edge VCK190 FPGA) inference benchmark; Latency (s): 42. - [Image Restoration on OpenAerialMap Sim-Degraded-Fixed Sim-Reference-Fixed (test)](): Image Restoration; OpenAerialMap Sim-Degraded-Fixed Sim-Reference-Fixed (test); PSNR: 27.5. - [Object Detection on DIOR Deg-Med (test)](): Object Detection; DIOR Deg-Med (test); mAP50: 75.52. - [Object Detection on DIOR Deg-High (test)](): Object Detection; DIOR Deg-High (test); mAP50: 72.37. - [Object Detection on DIOR Reference (test)](): Object Detection; DIOR Reference (test); mAP@0.50: not recorded. ## Original sources and implementation [Original paper]() [PDF]()