arXiv subjects

Ali Al-Zawqari

Publications and source records attributed to Ali Al-Zawqari.

6 recordsLinked to original sources

arXiv2026

MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration

Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surveillance, au- tonomous navigation, remote sensing, and inspection in poorly lit industrial environments. Most LLIE methods rely on output- level reconstruction losses that supervise only the final restored image, leaving the intermediate feature recovery process weakly constrained. This paper proposes MirrorDistill, an illumination- aware latent distillation framework that links the low-light and clean domains through feature mirroring. During training, a shared encoder and an exponential-moving-average teacher decoder process the clean reference image to generate clean- domain latent targets. These targets supervise the low-light student at two levels: raw encoder features and standardized multi-scale decoder projections. The alignment is applied layer by layer, while a proposed illumination-aware weighting scheme gives greater emphasis to underexposed regions. The teacher and reference branches are used only during training, so inference requires only the lightweight student encoder-decoder and in- troduces no teacher-side computational cost. Under evaluation on the standard LOL benchmarks, MirrorDistill outperforms the state-of-the-art methods on the real-captured LOL-v2-Real set, while having the lowest compute complexity (GMACs) and while remaining competitive on the LOL-v1 and LOL-v2-Synthetic datasets. Ablation studies further show the contributions of the encoder mirror, decoder mirror, and illumination-aware weighting. Finally, we release our code as open-source for the benefit of future research.

cs.CV↗

arXiv2026

IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders

This letter presents a novel training approach and loss function for learning low-light image enhancement auto-encoders. Our approach revolves around the use of a teacher-student auto-encoder setup coupled to a progressive learning approach where multi-scale information from clean image decoder feature maps is distilled into each layer of the student decoder in a mirrored fashion using a newly-proposed loss function termed Illumination-Aware Mirror Loss (IAML). IAML helps aligning the feature maps within the student decoder network with clean feature maps originating from the teacher side while taking into account the effect of lighting variations within the input images. Extensive benchmarking of our proposed approach on three popular low-light image enhancement datasets demonstrate that our model achieves state-of-the-art performance in terms of average SSIM, PSNR and LPIPS reconstruction accuracy metrics. Finally, ablation studies are performed to clearly demonstrate the effect of IAML on the image reconstruction accuracy.

cs.CV↗

arXiv2025

Learning to Control Dynamical Agents via Spiking Neural Networks and Metropolis-Hastings Sampling

Spiking Neural Networks (SNNs) offer biologically inspired, energy-efficient alternatives to traditional Deep Neural Networks (DNNs) for real-time control systems. However, their training presents several challenges, particularly for reinforcement learning (RL) tasks, due to the non-differentiable nature of spike-based communication. In this work, we introduce what is, to our knowledge, the first framework that employs Metropolis-Hastings (MH) sampling, a Bayesian inference technique, to train SNNs for dynamical agent control in RL environments without relying on gradient-based methods. Our approach iteratively proposes and probabilistically accepts network parameter updates based on accumulated reward signals, effectively circumventing the limitations of backpropagation while enabling direct optimization on neuromorphic platforms. We evaluated this framework on two standard control benchmarks: AcroBot and CartPole. The results demonstrate that our MH-based approach outperforms conventional Deep Q-Learning (DQL) baselines and prior SNN-based RL approaches in terms of maximizing the accumulated reward while minimizing network resources and training episodes.

cs.AI↗

arXiv2025

Benchmarking Online Object Trackers for Underwater Robot Position Locking Applications

Autonomously controlling the position of Remotely Operated underwater Vehicles (ROVs) is of crucial importance for a wide range of underwater engineering applications, such as in the inspection and maintenance of underwater industrial structures. Consequently, studying vision-based underwater robot navigation and control has recently gained increasing attention to counter the numerous challenges faced in underwater conditions, such as lighting variability, turbidity, camera image distortions (due to bubbles), and ROV positional disturbances (due to underwater currents). In this paper, we propose (to the best of our knowledge) a first rigorous unified benchmarking of more than seven Machine Learning (ML)-based one-shot object tracking algorithms for vision-based position locking of ROV platforms. We propose a position-locking system that processes images of an object of interest in front of which the ROV must be kept stable. Then, our proposed system uses the output result of different object tracking algorithms to automatically correct the position of the ROV against external disturbances. We conducted numerous real-world experiments using a BlueROV2 platform within an indoor pool and provided clear demonstrations of the strengths and weaknesses of each tracking approach. Finally, to help alleviate the scarcity of underwater ROV data, we release our acquired data base as open-source with the hope of benefiting future research.

cs.RO↗

arXiv2025

Co-Design of a Robot Controller Board and Indoor Positioning System for IoT-Enabled Applications

This paper describes the development of a cost-effective yet precise indoor robot navigation system composed of a custom robot controller board and an indoor positioning system. First, the proposed robot controller board has been specially designed for emerging IoT-based robot applications and is capable of driving two 6-Amp motor channels. The controller board also embeds an on-board micro-controller with WIFI connectivity, enabling robot-to-server communications for IoT applications. Then, working together with the robot controller board, the proposed positioning system detects the robot's location using a down-looking webcam and uses the robot's position on the webcam images to estimate the real-world position of the robot in the environment. The positioning system can then send commands via WIFI to the robot in order to steer it to any arbitrary location in the environment. Our experiments show that the proposed system reaches a navigation error smaller or equal to 0.125 meters while being more than two orders of magnitude more cost-effective compared to off-the-shelve motion capture (MOCAP) positioning systems.

cs.RO↗

arXiv2024

Automating the Design of Multi-band Microstrip Antennas via Uniform Cross-Entropy Optimization

Automating the design of microstrip antennas has been an active area of research for the past decade. By leveraging machine learning techniques such as Genetic Algorithms (GAs) or, more recently, Deep Neural Networks (DNNs), a number of work have demonstrated the possibility of producing non-trivial antenna geometries that can be efficient in terms of area utilization or be used in complex multi-frequency-band scenarios. However, both GAs and DNNs are notoriously compute-expensive, often requiring hour-long run times in order to produce new antenna geometries. In this paper, we propose to explore the novel use of Cross-Entropy optimization as a Monte-Carlo sampling technique for optimizing the geometry of patch antennas given a target $S_{11}$ scattering parameter curve that a user wants to obtain. We compare our proposed Uniform Cross-Entropy (UCE) method against other popular Monte-Carlo optimization techniques such as Gaussian Processes, Forest optimization and baseline random search approaches. We demonstrate that the proposed UCE technique outperforms the competing methods while still having a reasonable compute complexity, taking around 16 minutes to converge. Finally, our code is released as open-source with the hope of being useful to future research.

eess.SP↗