This paper examines a hybrid classical-quantum workflow for speckle-oriented image denoising, in which denoising is formulated as a discrete filter-parameter selection problem over image batches. Candidate convolution kernels are evaluated using batch-averaged peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), and the best-performing kernel is deployed within a variance-guided adaptive filtering stage. The selected kernel configuration is then encoded into a quantum register and marked using a Grover oracle, followed by amplitude amplification to increase the likelihood of retrieving the target configuration upon measurement. In this formulation, the quantum circuit serves to demonstrate parameter encoding, oraclebased marking, and probabilistic retrieval consistent with the classically selected optimum, rather than replacing classical fitness evaluation. Experiments conducted on speckle-contaminated image batches from multiple imaging modalities show that the optimized kernel provides stable denoising performance, while the quantum subroutine reproduces the target configuration with high probability under practical circuit-depth constraints.
This paper examines a hybrid classical-quantum workflow for speckle-oriented image denoising, in which denoising is formulated as a discrete filter-parameter selection problem over image batches. Candidate convolution kernels are evaluated using batch-averaged peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), and the best-performing kernel is deployed within a variance-guided adaptive filtering stage. The selected kernel configuration is then encoded into a quantum register and marked using a Grover oracle, followed by amplitude amplification to increase the likelihood of retrieving the target configuration upon measurement. In this formulation, the quantum circuit serves to demonstrate parameter encoding, oraclebased marking, and probabilistic retrieval consistent with the classically selected optimum, rather than replacing classical fitness evaluation. Experiments conducted on speckle-contaminated image batches from multiple imaging modalities show that the optimized kernel provides stable denoising performance, while the quantum subroutine reproduces the target configuration with high probability under practical circuit-depth constraints.
Medical image denoising remains challenging because imaging modalities and acquisition conditions produce heterogeneous and non-stationary noise. Although recent deep-learning and diffusion-based approaches achieve strong restoration performance, many methods rely on fixed transformations or require substantial computational resources. This work proposes the Noise-Adaptive Quantum Attention Network (NAQAN), a hybrid quantum–classical framework for noise-conditioned medical image denoising. NAQAN combines a lightweight convolutional encoder–decoder with an eight-qubit variational quantum attention mechanism whose circuit parameters are dynamically modulated by a specified noise-level conditioning variable. Feature-wise Linear Modulation (FiLM) provides complementary classical conditioning, while residual learning is used for image reconstruction. The present implementation is noise-conditioned rather than fully blind; the corresponding noise level is supplied to the model during both training and evaluation. Experiments on RetinaMNIST, OCTMNIST, Diabetic Retinopathy, and BraTS MRI under Gaussian, speckle, and Poisson corruption demonstrate consistent restoration performance across different imaging modalities and noise conditions. On BraTS MRI, NAQAN achieves a PSNR of 39.11dB and an SSIM of 0.9548. Controlled comparisons with classical denoising baselines and a parameter-matched classical attention variant further evaluate the contribution of the proposed quantum attention mechanism. NAQAN performs denoising through a single forward inference pass; however, simulation of the quantum circuit introduces additional computational overhead relative to the matched classical variant. These results demonstrate the potential of noise-conditioned hybrid quantum–classical attention for medical image restoration while motivating further evaluation on physical quantum hardware and clinically oriented downstream tasks.
Abstract Image denoising is essential for removing noise in images caused by electric device malfunctions or other factors during image acquisition. It ensures the preservation of image quality and accurate interpretation. Many convolutional autoencoder algorithms have proven effective in image denoising. Owing to their promising efficiency, quantum computers have gained popularity. This paper proposes a method, the quantum convolutional autoencoder (QCAE), which enhances traditional convolutional autoencoders by replacing their latent space with a quantum counterpart implemented via a quantum approximate optimization algorithm (QAOA)-inspired ansatz circuit. To enhance efficiency, we leveraged the advantages of the QAOA-incorporated parameter-shift rule to identify an optimized cost function, facilitating effective learning from data and gradient computation on an actual quantum computer. The proposed QCAE method outperformed its classical counterpart as it exhibited lower training loss and a higher structural similarity index (SSIM) value. QCAE also outperformed its classical counterpart in denoising the MNIST dataset by up to 40% in terms of SSIM value, confirming its enhanced capabilities in real-world applications. Evaluation of QAOA performance across different circuit configurations and layer variations showed that our technique outperformed other circuit designs by 25% on average.
Quantum information technologies are reshaping communication systems, but reliable integration of classical data, particularly images, into quantum frameworks remains a challenge. Circuit-based quantum image encoding methods are susceptible to noise-induced degradation, which undermines reproducibility and reliability. Here, we investigate the impact of quantum noise channels across the encoding and measurement stages within a hybrid quantum-classical distributed system. We also introduce noise into selected gate operations and measurements to demonstrate its distinct effects on the quantum circuit. To quantify the results, we compute the mean squared error (MSE), the structural similarity index measure (SSIM), and the peak signal-to-noise ratio (PSNR), and benchmark the results across various settings of the noise parameter. Finally, we present experimental results highlighting how image complexity affects encoding robustness using the Linnaeus and MNIST datasets. We anticipate that the presented results will contribute to the development of dependable quantum-classical orchestration strategies for resilient image processing.
Synthetic Aperture Radar (SAR) imaging is crucial in remote sensing due to its ability to produce high-resolution images regardless of weather conditions or daylight. However, SAR images often suffer from various types of noise, especially speckle noise, which degrades image quality and complicates data analysis. Traditional noise reduction techniques face challenges in balancing noise suppression with the preservation of image details. Recent deep learning approaches, such as U-Net architectures, have made strides in addressing these issues. Simultaneously, quantum computing has emerged as a promising field that can potentially enhance computational methods in image processing. We propose a hybrid classical-quantum U-Net framework that integrates quantum-classical algorithms with tensor networks for improved noise reduction in SAR images. Leveraging the representational capacity of tensor networks and the computational strengths of quantum algorithms, our method aims to surpass the limitations of classical techniques in managing complex noise patterns. In our architecture, certain layers of the U-Net are implemented using quantum circuits specifically optimized for noise suppression. The inclusion of tensor networks enables efficient handling of high-dimensional data within the hybrid model. The idea is to perform extensive experiments on standard SAR datasets to demonstrate that our hybrid U-Net outperforms traditional denoising methods and purely classical deep learning models in both noise reduction and detail preservation. Quantitative assessments using metrics like Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) would be used for comparison. Moreover, we will evaluate the computational efficiency of our approach, underscoring the potential of quantum computing to expedite complex image processing tasks. This work aims to highlight the feasibility and benefits of integrating quantum computing into practical remote sensing applications. Our hybrid quantum-classical U-Net architecture with tensor networks paves the way for advanced noise reduction techniques in SAR imaging and potentially other domains. Future research will focus on optimizing quantum circuit designs for specific noise types and exploring the scalability of our approach alongside advancements in quantum hardware.
Quantum Reservoir Computing (QRC) leverages the natural dynamics of quantum systems for information processing, without requiring a fault-tolerant quantum computer. In this work, we apply QRC within a hybrid quantum classical framework for image denoising. The quantum reservoir is implemented using a Rydberg atom array, while a classical neural network serves as the readout layer. To prepare the input, images are first compressed using Principal Component Analysis (PCA), reducing their dimensionality to match the size of the atom array. Each feature vector is encoded into local detuning parameters of a time-dependent Hamiltonian governing the Rydberg system. As the system evolves, it generates nonlinear embeddings through the measurement of observables across multiple time steps. These temporal embeddings capture complex correlations, which are fed into a classical neural network to reconstruct the denoised images. To evaluate performance, we compare this QRC-assisted model against a baseline architecture consisting of PCA followed by a dense neural network, trained under identical conditions. Our results show that the QRC-based approach achieves improved image sharpness and similar structural recovery compared to the PCA-based model. We demonstrate the practical viability of this framework through experiments on QuEra's Aquila neutral-atom processor, leveraging its programmable atom arrays to physically realize the reservoir dynamics.
Quantum image processing (QIP) is still a promising area as the noise of qubit, decoherence and limitations of encoding make it difficult for the current quantum hardware.This paper presents a combined Intelligent Quantum Image Denoising Framework, which uses FRQI and deep learning-based restoration, to enhance the quality and trustworthiness of images in quantum-classical hybrid areas.The short overview of related studies points out the classical filters and shallow neural models denoising methods, which are not able to generalize to quantum noise.To fill this void, a Convolutional Neural Network (CNN) is trained on the FRQI-encoded images simulated with Gaussian, saltand-pepper, and depolarizing noise.The approach uses confidence-based thresholding for restoration of adaptive pixels and measures the results with PSNR, SSIM, and MSE metrics.The experimental outcomes exhibit a considerable rise in the signal-to-noise ratio and the integrity of the structure when compared to the standard denoising techniques.The research indicates that the suggested combination of different methods has the capability to get rid of quantum noise yet at the same time allow the main image features to be seen.The steps for the next research will be applying the model to actual quantum simulators like Qiskit, creating better qubit usage, and widening the application of the framework to high-resolution images for quantum vision in real-world scenarios.