arXiv subjects

Cédric Léonard

Publications and source records attributed to Cédric Léonard.

4 recordsLinked to original sources

arXiv2026

In-orbit operation of a programmable quantum photonic processor

Quantum technologies promise computational capabilities beyond the reach of classical systems. A forward-looking application lies in satellite missions, which increasingly depend on onboard computing under stringent constraints on size, weight and power. Quantum photonics is particularly attractive here: photon interference can enhance the machine-learning models needed to process large onboard data volumes, at fixed hardware resources. However, harnessing this interference requires more than generating single photons, as they must remain mutually indistinguishable: a fragile condition that is hard to maintain within the technically demanding framework of a space mission, which includes a rocket launch, strong thermal drifts, and radiation. This is why quantum states of light, though already generated and transmitted in orbit for secure communication and fundamental tests, have never been used as a computational resource. Here, we report a programmable quantum photonic platform operating on a nanosatellite, processing two photons in a six-mode universal integrated circuit. By programming distinct unitaries and tuning the photons into indistinguishability, we observe two-photon interference, establishing the on-board generation, manipulation and detection of non-classical light. This extends space-based technologies towards in-orbit quantum-assisted computing, for instance local encoding of Earth-observation data, or nodes in a distributed quantum network.

quant-ph↗

arXiv2026

Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Binary Building Segmentation

High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of pixel-wise annotation, which makes it challenging for human annotators to label every pixel accurately. Annotation errors can significantly degrade the performance and robustness of modern segmentation models, motivating the need for reliable mechanisms to identify and quantify noisy training samples. This paper introduces a novel data-centric benchmark, together with a new, publicly available binary building segmentation dataset. This specific task serves as a representative and practically relevant testbed that enables controlled experimentation with different annotation perturbations. Furthermore, we also introduce two techniques for identifying, quantifying, and ranking training samples according to their level of label noise in remote sensing semantic segmentation. Such proposed methods leverage complementary strategies based on model uncertainty, prediction consistency, and representation analysis, and consistently outperform established baselines across a range of experimental settings. The outcomes of this work are publicly available at https://github.com/keillernogueira/label_noise_segmentation.

cs.CV↗

arXiv2026

Hardware-Aware Deployment of Joint SAR Compression and Despeckling on FPGA

Next-generation Synthetic Aperture Radar (SAR) missions will generate data far faster than they can downlink, making onboard data reduction essential for near-real-time Earth observation. Learned Image Compression (LIC) offers better rate-distortion performance than handcrafted codecs used operationally today, and recent work shows that simultaneously despeckling and compressing SAR imagery enables better representation capacity while unlocking higher compression rates. These methods, however, have yet to be confronted with the strict power, compute, and operational constraints of spaceborne systems. In this work, we bridge this gap by deploying a joint SAR Despeckling and Data Compression (DDC) framework on an embedded ZCU102 FPGA-based platform, introducing model adaptations that respect the accelerator's fixed-point arithmetic and limited set of supported operations. We evaluate four model topologies across precision levels and across CPU, GPU, and FPGA platforms, revealing several findings with direct design implications. We find that replacing conventional GDN activation functions with plain ReLU improves quality on SAR, suggesting that design principles established for compression of natural images do not necessarily transfer to SAR imagery. In addition, we demonstrate that residual blocks offer little representational benefit for ten times the compute, and show that the FPGA is the most energy-efficient of the platforms tested. Together, these results set a functioning edge deployment workflow and an evidence-based starting point for onboard SAR compression. The code is available at https://github.com/CedricLeon/SAR_DDC_FPGA.

eess.IV↗

arXiv2026

FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Review

New UAV technologies and the NewSpace era are transforming Earth Observation missions and data acquisition. Numerous small platforms generate large data volume, straining bandwidth and requiring onboard decision-making to transmit high-quality information in time. While Machine Learning allows real-time autonomous processing, FPGAs balance performance with adaptability to mission-specific requirements, enabling onboard deployment. This review systematically analyzes 68 experiments deploying ML models on FPGAs for Remote Sensing applications. We introduce two distinct taxonomies to capture both efficient model architectures and FPGA implementation strategies. For transparency and reproducibility, we follow PRISMA 2020 guidelines and share all data and code at https://github.com/CedricLeon/Survey_RS-ML-FPGA.

cs.LG↗