Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2609.36702

Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation

Xue Yang, Rigui Zhou, Dax Enshan Koh, Siong Thye Goh, Yitao Tang, ShiZheng Jia, Young-Wook Cho, Hongyu Chen

quant-phcs.CVSubmitted Sep 29, 2026• Announced Sep 30, 2026• 0 citations
arXivHTMLPDF

Abstract

Quantum Generative Adversarial Networks (QGANs) have emerged as representative generative models in the Noisy Intermediate-Scale Quantum (NISQ) era and have attracted increasing attention in quantum machine learning. However, most existing QGAN methods rely on patch-based decomposition strategies, which weaken the global consistency of generated images and increase quantum resource overhead. In this work, we investigate a simpler approach: pixel-level, end-to-end image generation using a single-quantum-circuit QGAN. By analyzing the structural matching relationship between the quantum prior and the target data distribution in Hilbert space, we provide a new theoretical perspective for understanding the training behavior of naive end-to-end QGANs. Specifically, we introduce the Quantum Fidelity Landscape (QFL), defined as the pairwise-fidelity structure induced by an ensemble of quantum states and preserved under shared unitary transformations of the quantum generation process. We show that, under a fixed Lipschitz readout, this invariant imposes a one-sided bound on decoded sample separation, motivating calibration of the prior-induced QFL before adversarial training. To validate this theoretical insight, we propose BasicQGAN, a QGAN framework incorporating quantum prior calibration. Before adversarial optimization, BasicQGAN aligns the prior-induced QFL with the data-induced QFL. Experimental results on small-scale grayscale image datasets show that BasicQGAN achieves stable and effective end-to-end pixel-level image generation while requiring fewer qubits and trainable parameters than representative patch-based quantum generators. Furthermore, experiments with different initial quantum-state ensembles show that QFL-calibrated ensembles achieve better generative performance.

AI Summary

This paper asks how the quantum latent prior affects training of single-circuit QGANs that generate complete pixel images rather than independent patches. It defines the quantum fidelity landscape (QFL) as an ensemble’s pairwise-fidelity matrix and uses its invariance under a shared unitary to motivate prior calibration before adversarial training. The analysis combines unitary invariance, measurement contractivity and the Fuchs–van de Graaf inequality. For a fixed readout whose classical post-processing is $L$-Lipschitz in total variation, decoded pairs satisfy $d(x_i,x_j)\leq L\sqrt{1-F(\rho_i,\rho_j)}$. For amplitude-magnitude vectors, it obtains $\|a_i-a_j\|_2^2\leq2(1-\sqrt{F(\rho_i,\rho_j)})$. These are one-sided separation constraints, not guarantees of distribution recovery. BasicQGAN calibrates product-state rotation-angle ranges by matching the prior and amplitude-encoded data’s empirical fidelity distributions using KDE, mean and variance discrepancies, then trains a shared circuit with WGAN-GP. Noise-free simulations cover MNIST at $16\times16$ and $28\times28$, plus small letter and shape datasets. On $16\times16$ digit 0, calibrated-prior FID is 20.38, versus 73.93 and 72.64 for two uncalibrated broad priors and 33.97 for an extremely narrow prior. The $16\times16$ generator uses eight qubits and 320 trainable parameters. Reported comparisons show lower FID than patch-based PQWGAN at $16\times16$, but higher FID than the baselines at $28\times28$. Stated limitations include ideal simulation without hardware or noise validation, small grayscale benchmarks, and degraded higher-resolution performance. Histogram calibration does not establish full geometric matching or successful generation.

Some signs of AI-generated textIncrementalSmall numerics onlyMissing comparisonOverclaims

Error found: The paper says BasicQGAN and PQWGAN(Global) use identical generator circuits to isolate prior calibration, but its resource table assigns them different qubit and parameter counts at both image resolutions. The training pseudocode minimizes the generated samples' critic score, reversing the stated WGAN-GP generator objective, although it is unclear whether this error occurs in the experimental implementation.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Related papers

Hybrid Quantum-Classical Generative Adversarial Network for Patch-Based Image Generation

Jen-Sheng Tsai, Li-Yin Cai

Quantum generative adversarial networks (QGANs) have attracted increasing attention for their potential to surpass classical generative models by leveraging the expressive power of parameterized quantum circuits (PQCs). However, in the current noisy intermediate-scale quantum era, the implementation of fully quantum algorithms is hindered by hardware limitations, restricting most existing approaches to low-resolution generated image. To address this challenge, we propose a hybrid quantum-classical generative adversarial network for patch-based image generation. Our method employs dual PQC-based generators that decompose images into structured patches, while local and global classical discriminators jointly capture local details and preserve global structural coherence. This design addresses scalability limitations of existing QGANs and mitigates patch-boundary artifacts, thereby enabling high-resolution image generation on hardware with restricted qubit counts. Experimental results validate the effectiveness of the proposed method, demonstrating improvements in image fidelity over existing baselines, and providing insights into the influence of qubit count on generative performance.

International Conference on Information and Communication Technology Convergence (ICTC)•Oct 14, 2025•0 citations

End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration

Xue Yang, Rigui Zhou, Shizheng Jia +5 more

Quantum Generative Adversarial Networks (QGANs) offer a promising path for learning data distributions on near-term quantum devices. However, existing QGANs for image synthesis avoid direct full-image generation, relying on classical post-processing or patch-based methods. These approaches dilute the quantum generator's role and struggle to capture global image semantics. To address this, we propose ReQGAN, an end-to-end framework that synthesizes an entire N=2^D-pixel image using a single D-qubit quantum circuit. ReQGAN overcomes two fundamental bottlenecks hindering direct pixel generation: (1) the rigid classical-to-quantum noise interface and (2) the output mismatch between normalized quantum statistics and the desired pixel-intensity space. We introduce a learnable Neural Noise Encoder for adaptive state preparation and a differentiable Intensity Calibration module to map measurements to a stable, visually meaningful pixel domain. Experiments on MNIST and Fashion-MNIST demonstrate that ReQGAN achieves stable training and effective image synthesis under stringent qubit budgets, with ablation studies verifying the contribution of each component.

quant-pharXiv:2603.18554•Mar 20, 2026•2 citations

Survey of Quantum Generative Adversarial Networks (QGAN) to Generate Images

Mohammadsaleh Pajuhanfard, Rasoul Kiani, Victor S. Sheng

Quantum Generative Adversarial Networks (QGANs) represent a useful development in quantum machine learning, using the particular properties of quantum mechanics to solve the challenges of data analysis and modeling. This paper brings up a general analysis of five QGAN architectures, focusing on their evolution, strengths, weaknesses, and limitations in noisy intermediate-scale quantum (NISQ) devices. Primary methods like Entangling Quantum GAN (EQ-GAN) and Quantum state fidelity (QuGAN) concentrate on stability, convergence, and robust performance on small-scale datasets such as 2 × 2 grayscale images. Intermediate models such as Image Quantum GAN (IQGAN) and Experimental Quantum GAN (EXQGAN) provide new ideas like trainable encoders and patch-based sub-generators that are scalable to 8 × 8 datasets with increasing noise resilience. The most advanced method is Parameterized Quantum Wasserstein GAN (PQWGAN), which uses a hybrid quantum-classical structure to obtain high-resolution image processing for 28 × 28 grayscale datasets while trying to maintain parameter efficiency. This study explores, analyzes, and summarizes critical problems of QGANs, including accuracy, convergence, parameter efficiency, image quality, performance metrics, and training stability under noisy conditions. In addition, developing QGANs can generate and train parameters in quantum approximation optimization algorithms. One of the useful applications of QGAN is generating medical datasets that can generate medical images from limited datasets to train specific medical models for the recognition of diseases.

Mathematics•Dec 6, 2024•30 citations

Hybrid Quantum–Classical Generative Adversarial Network for High-Resolution Image Generation

Shu Lok Tsang, Maxwell T. West, Sarah Erfani +1 more

Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in problems such as classification and identification tasks. A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks. The existing work on QGANs is still limited to small-scale proof-of-concept examples based on images with significant down-scaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities over existing quantum techniques by generating 28×28 pixels grey-scale images without dimensionality reduction or classical pre/post-processing on multiple classes of the standard MNIST and Fashion MNIST datasets, which achieves comparable results to classical frameworks with three orders of magnitude less trainable generator parameters. To gain further insight into the working of our hybrid approach, we systematically explore the impact of its parameter space by varying the number of qubits, the size of image patches, the number of layers in the generator, the shape of the patches and the choice of prior distribution. Our results show that increasing the quantum generator size generally improves the learning capability of the network. The developed framework provides a foundation for future design of QGANs with optimal parameter set tailored for complex image generation tasks

arXiv:2212.11614•IEEE Transactions on Quantum Engineering•Jan 1, 2023•128 citations

Quantum Generative Adversarial Networks in the NISQ Era: A Survey of Architectures, Objectives, and Evaluation Practices (2023-2025)

Sakthi Prabhu Gunasekar, Prasanna Kumar Rangarajan

Quantum Generative Adversarial Networks (QGANs) incorporate quantum models, predominantly parameterized quantum circuits (PQCs), into adversarial learning frameworks for generative modeling within Noisy Intermediate Scale Quantum (NISQ) limitations. In the past three years, QGAN research has transitioned towards hybrid quantum-classical architectures, patch-based and latent-based scaling methodologies, and stability-focused objectives, including Wasserstein losses, gradient penalties, mutual-information regularization, and learned priors. This survey examines representative QGAN literature from 2023 to 2025, emphasizing algorithmic objectives, reported experimental results, evaluation methodologies, and practical constraints. This paper proposes a multidimensional taxonomy for organizing recent QGAN research based on architectural design, training objectives, scalability strategies, and evaluation practices. It highlights persistent issues in benchmarking, scalability, and hardware realism by comparing datasets, metrics, and architectural patterns across studies, offering a structured overview of the current QGAN research landscape.

International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT)•Apr 1, 2026•0 citations

CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-to-End Image Generation

Xue Yang, Rigui Zhou, ShiZheng Jia +7 more

Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits. Existing amplitude-based approaches face two key limitations: pixel locations are typically encoded by computational-basis indices or address qubits, causing quantum resources to grow with image resolution; meanwhile, jointly decoding many pixels from normalized quantum states introduces probability competition among pixels and limits precise pixel-wise control. To address these issues, we reformulate quantum image generation as coordinate-conditioned implicit function learning. Our method takes spatial coordinates and latent variables as inputs, uses a classical embedding network to generate input-dependent circuit parameters, and evaluates a variational quantum circuit at each coordinate. Pixel intensities are directly obtained from the expectation value of a dedicated color qubit, and a complete image is generated by querying all spatial coordinates. This design decouples image resolution from address-qubit requirements and avoids shared probability-normalization constraints across pixels. We further design a specialized variational quantum circuit to provide structural inductive bias for coordinate-conditioned generation. Simulated experiments on two benchmark datasets show that our method outperforms FRQI-based generation and PQWGAN in visual and quantitative quality while using fewer qubits, and also achieves better generation quality than the corresponding classical baseline.

quant-pharXiv:2608.11884•Aug 13, 2026•0 citations
Quantum Generative Adversarial Networks (QGANs) have emerged as representative generative models in the Noisy Intermediate-Scale Quantum (NISQ) era and have attracted increasing attention in quantum machine learning. However, most existing QGAN methods rely on patch-based decomposition strategies, which weaken the global consistency of generated images and increase quantum resource overhead. In this work, we investigate a simpler approach: pixel-level, end-to-end image generation using a single-quantum-circuit QGAN. By analyzing the structural matching relationship between the quantum prior and the target data distribution in Hilbert space, we provide a new theoretical perspective for understanding the training behavior of naive end-to-end QGANs. Specifically, we introduce the Quantum Fidelity Landscape (QFL), defined as the pairwise-fidelity structure induced by an ensemble of quantum states and preserved under shared unitary transformations of the quantum generation process. We show that, under a fixed Lipschitz readout, this invariant imposes a one-sided bound on decoded sample separation, motivating calibration of the prior-induced QFL before adversarial training. To validate this theoretical insight, we propose BasicQGAN, a QGAN framework incorporating quantum prior calibration. Before adversarial optimization, BasicQGAN aligns the prior-induced QFL with the data-induced QFL. Experimental results on small-scale grayscale image datasets show that BasicQGAN achieves stable and effective end-to-end pixel-level image generation while requiring fewer qubits and trainable parameters than representative patch-based quantum generators. Furthermore, experiments with different initial quantum-state ensembles show that QFL-calibrated ensembles achieve better generative performance.
This paper asks how the quantum latent prior affects training of single-circuit QGANs that generate complete pixel images rather than independent patches. It defines the quantum fidelity landscape (QFL) as an ensemble’s pairwise-fidelity matrix and uses its invariance under a shared unitary to motivate prior calibration before adversarial training.
The analysis combines unitary invariance, measurement contractivity and the Fuchs–van de Graaf inequality. For a fixed readout whose classical post-processing is LLL-Lipschitz in total variation, decoded pairs satisfy d(xi,xj)≤L1−F(ρi,ρj)d(x_i,x_j)\leq L\sqrt{1-F(\rho_i,\rho_j)}d(xi​,xj​)≤L1−F(ρi​,ρj​)​. For amplitude-magnitude vectors, it obtains ∥ai−aj∥22≤2(1−F(ρi,ρj))\|a_i-a_j\|_2^2\leq2(1-\sqrt{F(\rho_i,\rho_j)})∥ai​−aj​∥22​≤2(1−F(ρi​,ρj​)​). These are one-sided separation constraints, not guarantees of distribution recovery. BasicQGAN calibrates product-state rotation-angle ranges by matching the prior and amplitude-encoded data’s empirical fidelity distributions using KDE, mean and variance discrepancies, then trains a shared circuit with WGAN-GP.
Noise-free simulations cover MNIST at 16×1616\times1616×16 and 28×2828\times2828×28, plus small letter and shape datasets. On 16×1616\times1616×16 digit 0, calibrated-prior FID is 20.38, versus 73.93 and 72.64 for two uncalibrated broad priors and 33.97 for an extremely narrow prior. The 16×1616\times1616×16 generator uses eight qubits and 320 trainable parameters. Reported comparisons show lower FID than patch-based PQWGAN at 16×1616\times1616×16, but higher FID than the baselines at 28×2828\times2828×28.
Stated limitations include ideal simulation without hardware or noise validation, small grayscale benchmarks, and degraded higher-resolution performance. Histogram calibration does not establish full geometric matching or successful generation.
Quantum generative adversarial networks (QGANs) have attracted increasing attention for their potential to surpass classical generative models by leveraging the expressive power of parameterized quantum circuits (PQCs). However, in the current noisy intermediate-scale quantum era, the implementation of fully quantum algorithms is hindered by hardware limitations, restricting most existing approaches to low-resolution generated image. To address this challenge, we propose a hybrid quantum-classical generative adversarial network for patch-based image generation. Our method employs dual PQC-based generators that decompose images into structured patches, while local and global classical discriminators jointly capture local details and preserve global structural coherence. This design addresses scalability limitations of existing QGANs and mitigates patch-boundary artifacts, thereby enabling high-resolution image generation on hardware with restricted qubit counts. Experimental results validate the effectiveness of the proposed method, demonstrating improvements in image fidelity over existing baselines, and providing insights into the influence of qubit count on generative performance.
Quantum Generative Adversarial Networks (QGANs) offer a promising path for learning data distributions on near-term quantum devices. However, existing QGANs for image synthesis avoid direct full-image generation, relying on classical post-processing or patch-based methods. These approaches dilute the quantum generator's role and struggle to capture global image semantics. To address this, we propose ReQGAN, an end-to-end framework that synthesizes an entire N=2^D-pixel image using a single D-qubit quantum circuit. ReQGAN overcomes two fundamental bottlenecks hindering direct pixel generation: (1) the rigid classical-to-quantum noise interface and (2) the output mismatch between normalized quantum statistics and the desired pixel-intensity space. We introduce a learnable Neural Noise Encoder for adaptive state preparation and a differentiable Intensity Calibration module to map measurements to a stable, visually meaningful pixel domain. Experiments on MNIST and Fashion-MNIST demonstrate that ReQGAN achieves stable training and effective image synthesis under stringent qubit budgets, with ablation studies verifying the contribution of each component.
Quantum Generative Adversarial Networks (QGANs) represent a useful development in quantum machine learning, using the particular properties of quantum mechanics to solve the challenges of data analysis and modeling. This paper brings up a general analysis of five QGAN architectures, focusing on their evolution, strengths, weaknesses, and limitations in noisy intermediate-scale quantum (NISQ) devices. Primary methods like Entangling Quantum GAN (EQ-GAN) and Quantum state fidelity (QuGAN) concentrate on stability, convergence, and robust performance on small-scale datasets such as 2 × 2 grayscale images. Intermediate models such as Image Quantum GAN (IQGAN) and Experimental Quantum GAN (EXQGAN) provide new ideas like trainable encoders and patch-based sub-generators that are scalable to 8 × 8 datasets with increasing noise resilience. The most advanced method is Parameterized Quantum Wasserstein GAN (PQWGAN), which uses a hybrid quantum-classical structure to obtain high-resolution image processing for 28 × 28 grayscale datasets while trying to maintain parameter efficiency. This study explores, analyzes, and summarizes critical problems of QGANs, including accuracy, convergence, parameter efficiency, image quality, performance metrics, and training stability under noisy conditions. In addition, developing QGANs can generate and train parameters in quantum approximation optimization algorithms. One of the useful applications of QGAN is generating medical datasets that can generate medical images from limited datasets to train specific medical models for the recognition of diseases.
Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in problems such as classification and identification tasks. A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks. The existing work on QGANs is still limited to small-scale proof-of-concept examples based on images with significant down-scaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities over existing quantum techniques by generating 28×28 pixels grey-scale images without dimensionality reduction or classical pre/post-processing on multiple classes of the standard MNIST and Fashion MNIST datasets, which achieves comparable results to classical frameworks with three orders of magnitude less trainable generator parameters. To gain further insight into the working of our hybrid approach, we systematically explore the impact of its parameter space by varying the number of qubits, the size of image patches, the number of layers in the generator, the shape of the patches and the choice of prior distribution. Our results show that increasing the quantum generator size generally improves the learning capability of the network. The developed framework provides a foundation for future design of QGANs with optimal parameter set tailored for complex image generation tasks
Quantum Generative Adversarial Networks (QGANs) incorporate quantum models, predominantly parameterized quantum circuits (PQCs), into adversarial learning frameworks for generative modeling within Noisy Intermediate Scale Quantum (NISQ) limitations. In the past three years, QGAN research has transitioned towards hybrid quantum-classical architectures, patch-based and latent-based scaling methodologies, and stability-focused objectives, including Wasserstein losses, gradient penalties, mutual-information regularization, and learned priors. This survey examines representative QGAN literature from 2023 to 2025, emphasizing algorithmic objectives, reported experimental results, evaluation methodologies, and practical constraints. This paper proposes a multidimensional taxonomy for organizing recent QGAN research based on architectural design, training objectives, scalability strategies, and evaluation practices. It highlights persistent issues in benchmarking, scalability, and hardware realism by comparing datasets, metrics, and architectural patterns across studies, offering a structured overview of the current QGAN research landscape.
Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits. Existing amplitude-based approaches face two key limitations: pixel locations are typically encoded by computational-basis indices or address qubits, causing quantum resources to grow with image resolution; meanwhile, jointly decoding many pixels from normalized quantum states introduces probability competition among pixels and limits precise pixel-wise control. To address these issues, we reformulate quantum image generation as coordinate-conditioned implicit function learning. Our method takes spatial coordinates and latent variables as inputs, uses a classical embedding network to generate input-dependent circuit parameters, and evaluates a variational quantum circuit at each coordinate. Pixel intensities are directly obtained from the expectation value of a dedicated color qubit, and a complete image is generated by querying all spatial coordinates. This design decouples image resolution from address-qubit requirements and avoids shared probability-normalization constraints across pixels. We further design a specialized variational quantum circuit to provide structural inductive bias for coordinate-conditioned generation. Simulated experiments on two benchmark datasets show that our method outperforms FRQI-based generation and PQWGAN in visual and quantitative quality while using fewer qubits, and also achieves better generation quality than the corresponding classical baseline.