Recent advancements in Single-Image Super-Resolution (SISR) using deep learning have significantly improved image restoration quality. However, the high computational cost of processing high-resolution images due to the large number of parameters in classical models, along with the scalability challenges of quantum algorithms for image processing, remains a major obstacle. In this paper, we propose the Quantum Image Enhancement Transformer for Super-Resolution (QUIET-SR), a hybrid framework that extends the Swin transformer architecture with a novel shifted quantum window attention mechanism, built upon variational quantum neural networks. QUIET-SR effectively captures complex residual mappings between low-resolution and high-resolution images, leveraging quantum attention mechanisms to enhance feature extraction and image restoration while requiring a minimal number of qubits, making it suitable for the Noisy Intermediate-Scale Quantum (NISQ) era. We evaluate our framework in MNIST (30.24 PSNR, 0.989 SSIM), FashionMNIST (29.76 PSNR, 0.976 SSIM) and the MedMNIST dataset collection, demonstrating that QUIET-SR achieves PSNR and SSIM scores comparable to state-of-the-art methods while using fewer parameters. Our efficient batching strategy directly enables massive parallelization on multiple QPU's paving the way for practical quantum-enhanced image super-resolution through coordinated QPU-GPU quantum supercomputing.
Recent advancements in Single-Image Super-Resolution (SISR) using deep learning have significantly improved image restoration quality. However, the high computational cost of processing high-resolution images due to the large number of parameters in classical models, along with the scalability challenges of quantum algorithms for image processing, remains a major obstacle. In this paper, we propose the Quantum Image Enhancement Transformer for Super-Resolution (QUIET-SR), a hybrid framework that extends the Swin transformer architecture with a novel shifted quantum window attention mechanism, built upon variational quantum neural networks. QUIET-SR effectively captures complex residual mappings between low-resolution and high-resolution images, leveraging quantum attention mechanisms to enhance feature extraction and image restoration while requiring a minimal number of qubits, making it suitable for the Noisy Intermediate-Scale Quantum (NISQ) era. We evaluate our framework in MNIST (30.24 PSNR, 0.989 SSIM), FashionMNIST (29.76 PSNR, 0.976 SSIM) and the MedMNIST dataset collection, demonstrating that QUIET-SR achieves PSNR and SSIM scores comparable to state-of-the-art methods while using fewer parameters. Our efficient batching strategy directly enables massive parallelization on multiple QPU's paving the way for practical quantum-enhanced image super-resolution through coordinated QPU-GPU quantum supercomputing.
Super-Resolution (SR) is a technique that has been exhaustively exploited and incorporates strategic aspects to image processing. As quantum computers gradually evolve and provide unconditional proof of a computational advantage at solving intractable problems over their classical counterparts, quantum computing emerges with the compelling argument of offering exponential speed-up to process computationally expensive operations. Envisioning the design of parallel, quantum-ready algorithms for near-term noisy devices and igniting Rapid and Accurate Image Super Resolution (RAISR), an implementation applying variational quantum computation is demonstrated for enhancing degraded imagery. This study proposes an approach that combines the benefits of RAISR, a non hallucinating and computationally efficient method, and Variational Quantum Eigensolver (VQE), a hybrid classical-quantum algorithm, to conduct SR with the support of a quantum computer, while preserving quantitative performance in terms of Image Quality Assessment (IQA). It covers the generation of additional hash-based filters learned with the classical implementation of the SR technique, in order to further explore performance improvements, produce images that are significantly sharper, and induce the learning of more powerful upscaling filters with integrated enhancement effects. As a result, it extends the potential of applying RAISR to improve low quality assets generated by low cost cameras, as well as fosters the eventual implementation of robust image enhancement methods powered by the use of quantum computation.
Abstract The combination of Transformer architectures with Quantum Computing has opened new directions in Quantum Natural Language Processing (QNLP) by leveraging the Transformer’s representational capacity together with the computational parallelism and high-dimensional feature space of quantum systems. However, existing approaches remain constrained by partial designs and limited integration, hindering scalability and trainability. This study introduces FitQT—a novel, fully integrated, and trainable quantum transformer that unifies three essential components: (1) a quantum multi-head attention mechanism employing a scaled Gaussian kernel, (2) a quantum feed-forward network, and (3) quantum residual connections. The residual connections stabilize gradient flow and facilitate the training of deeper quantum circuits, while the attention and feed-forward components jointly enhance representational capacity. Evaluations on sentiment analysis datasets demonstrate FitQT’s effectiveness. On the IMDb dataset, FitQT improves accuracy by 14.89% over the baseline Quantum Self-Attention Network and achieves competitive task-level performance relative to BERT-Base, despite being trained from scratch without large-scale pretraining, while requiring only 2,595 parameters and substantially reduced training time. Moreover, FitQT achieves state-of-the-art performance compared to prior quantum-based transformer architectures such as QSANN and QMSAN. These results highlight the importance of incorporating classical deep learning principles into quantum architectures and provide a practical foundation for scalable, resource-efficient QNLP systems suitable for the noisy intermediate-scale quantum era.
Given the recent prominence of Noisy Intermediate Scale Quantum (NISQ) devices, hybrid quantum-classical neural networks have recently drawn a lot of excitement as a potential solution to improving learning efficiency. Our current paper describes a Hybrid Quantum-Classical Convolutional Neural Network (HQCNN) which is defined as a pretrained backbone of ResNet-18 and a small quantum-enhanced feature-transformation layer of Qiskit. The convolutional high-dimensional features are reduced to the classical eight-dimensional one, which in turn is encoded into a four-qubit parameterized quantum circuit. The resultant quantum expectation values are combined with the compressed features to come up with a hybridized representation of twelve dimensions, used to classify multi-class dataset. Experimental analysis of CIFAR10 data has shown that the suggested HQCNN achieves a test accuracy of 94.74% and improves class-wise precision, recall, and F1-scores than a number of existing hybrid models while using a significantly smaller number of latent features. More investigation into the quantum module indicates that it is predictable about scalability to batch, resistant to perturbations in features, and efficiently performed by evaluating circuit vectors. These results indicate that compact and expressive representations of images that can be helpful in the NISQ era can be acquired using hybrid architectures, thus providing a practical way to forward the benefits of quantum to modern deep-learning pipelines.
Hyperspectral images (HSIs) have drawn considerable attention over the last decade thanks to their high spectral resolution. However, as hardware limitations often cause the low spatial resolution of HSIs compared to traditional RGB and multispectral images, the hyperspectral image super-resolution (HSR) problem becomes crucial in facilitating the subsequent material identification applications. Recently, we developed hyperspectral quantum deep network (HyperQUEEN) for satellite data restoration, thereby proving that quantum features do play some role in developing high-performance inverse imaging algorithms. Before HyperQUEEN, which elegantly performs the hyperspectral matrix/tensor factorization via the so-called low-rank module, other existing quantum image processing tasks can only achieve basic geometry transforms or simple classification-level tasks. In this work, we go a step further by investigating the quantum implementation of multi-scale feature fusion (MF) transformer and applying the HyperQUEEN-MF to solve the challenging inverse problem known as single HSR (SHSR). By learning multi-scale quantum features, the proposed HyperQUEEN-MF does show outstanding SHSR performances, while the experimental results also show the feasibility of quantum-driven hyperspectral super-resolution. This creates a door for solving other advanced challenging inverse problems via quantum feature information extraction and processing.
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.
This paper proposes a quantum computing-based algorithm to solve the single image super-resolution (SISR) problem. One of the well-known classical approaches for SISR relies on the well-established patch-wise sparse modeling of the problem. Yet, this field’s current state of affairs is that deep neural networks (DNNs) have demonstrated far superior results than traditional approaches. Nevertheless, quantum computing is expected to become increasingly prominent for machine learning problems soon. As a result, in this work, we take the privilege to perform an early exploration of applying a quantum computing algorithm to this important image enhancement problem, i.e., SISR. Among the two paradigms of quantum computing, namely universal gate quantum computing and adiabatic quantum computing (AQC), the latter has been successfully applied to practical computer vision problems, in which quantum parallelism has been exploited to solve combinatorial optimization efficiently. This work demonstrates formulating quantum SISR as a sparse coding optimization problem, which is solved using quantum annealers accessed via the D-Wave Leap platform. The proposed AQC-based algorithm is demonstrated to achieve improved speed-up over a classical analog while maintaining comparable SISR accuracy1.