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

A Hybrid Quantum-Classical GAN with Classical Critic for Multi-Conditional Image Generation

Zhenyu Ta, Dongsheng Cai

Published Mar 5, 2026• 0 citations
Publisher

Abstract

Abstract Quantum machine learning (QML) has garnered significant attention for its potential to outperform classical machine learning.A notable area within QML is quantum generative adversarial networks (QGANs), which serve as the quantum equivalent to classical GANs, commonly used in image processing and generation.However, the content of images generated by existing QGANs is still uncontrollable.In this work, we introduce a conditional encoder for the quantum generator, enabling it to controllably produce multiple image types.While this approach can, in principle, be extended to any number of conditional generations, its practical applicability is limited by the finite qubit resources available.Our results show that it can generate images of satisfactory quality, with a Frechet Inception Distance (FID) score of $201.6$, a Kernel Inception Distance (KID) score of $0.281$, and a Learned Perceptual Image Patch Similarity (LPIPS) score of $0.461$.Through quantum noise experiments, we show that when the noise intensity reaches $0.2$, the relative changes in FID, KID, and LPIPS remain below $5\%$, indicating that the model is robust to moderate noise levels.Furthermore, in comparative experiments against without multicondition or limitted multicondition, our method outperforms the strongest baseline by $3\%-11\%$ , thereby demonstrating its stable superiority over current approaches.

DOI
10.21203/rs.3.rs-8326814/v1

Related papers

BAE-QCGAN: a hybrid quantum-classical generative adversarial network

Han Qi, Zhichao Liang, Abdullah Gani +2 more

With the speedy advancement of hardware, quantum machine learning has garnered widespread attention. Generative Adversarial Networks (GANs) are widely adopted quantum machine learning frameworks used for providing highstandard audio content, images, and videos. Utilizing quantum computing for image generation has been found to offer several potential advantages over non-quantum technologies. Current quantum Generative Adversarial Networks (QGANs) still face challenges, such as the inability to generate high-quality images. In the current investigation, we propose a QGAN model based on Autoencoders (BAE-QCGAN) and evaluate its performance. By drawing upon the entanglement and expression capabilities of quantum circuits, our composite system outperforms classical GANs in terms of Frechet Inception Distance, requiring fewer training parameters and fewer iterations to converge. We also demonstrate that BAEQCGAN outperforms another quantum GAN, the patch-GAN, and is adapted for existing Noisy Intermediate Scale Quantum (NISQ) computers.

International Conference on Physics and Quantum Computing (ICPQC)•Aug 5, 2025•0 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•111 citations

Quantum-classical synergy: enhancing quantum generative adversarial networks for lmage synthesis

QuanGong Ma, Chaolong Hao, Nianwen Si +5 more

Quantum Generative Adversarial Networks (QGANs), as a rising paradigm in Quantum Machine Learning, have shown promising potential in image generation and processing. However, their output quality remains suboptimal, and existing research is largely limited to small-scale, proof-of-concept studies. In this work, we propose a hybrid quantum-classical GAN architecture, where the generator integrates parameterized quantum circuits (PQCs) and classical neural networks. This integration significantly enhances the visual quality of generated images. Our model leverages the complementary strengths of quantum and classical components and outperforms existing methods (Tsang et al. in IEEE Trans. Quantum Eng. 4:1–19, 2023 ; Gulrajani et al. in Proceedings of the 31st international conference on neural information processing systems. NIPS’17, Red Hook, pp. 5769–5779, 2017 ), particularly in terms of image fidelity. Experiments conducted on the MNIST family of datasets show that our hybrid approach achieves a 20.26% average reduction in Fréchet Inception Distance. Furthermore, it improves the Structural Similarity Index Measure, Cosine Similarity, and Peak Signal-to-Noise Ratio by 26.04%, 2.22%, and 7.62%, respectively. These results highlight the effectiveness of combining quantum computing with machine learning, and underscore the potential of hybrid quantum-classical models in advancing generative tasks.

EPJ Quantum Technology•Sep 29, 2025•6 citations

Quantum generative adversarial networks with dual generators

Quangong Ma, Chaolong Hao, Nianwen Si +1 more

Abstract Quantum generative adversarial networks (QGANs) have demonstrated strong capabilities in tasks like synthetic data generation and detecting anomalies. Recent developments have increasingly integrated traditional machine learning techniques to boost the performance of QGANs. Motivated by this progress, we propose an innovative QGAN architecture that incorporates a classical learning component and employs a dual-generator design. Our approach improves upon the traditional hybrid quantum–classical GAN structure and introduces a redesigned loss function tailored for the new model. Experiments on multiple datasets indicate that our method surpasses previous techniques in image generation quality, achieving a 1.38% average reduction in Fréchet inception distance scores compared to the current state-of-the-art, and improvements of 6.52%, 0.36%, and 0.38% in structural similarity index, cosine similarity, and peak signal-to-noise ratio metrics, respectively. Additionally, our architecture supports the generation of larger images (up to 78 × 78 ), as verified on the CelebA dataset. Simulations conducted in noisy conditions further confirm the robustness and effectiveness of both the proposed architecture and loss function.

Machine Learning Science and Technology•Sep 25, 2025•1 citation

Hybrid Quantum-Classical Generative Adversarial Networks With Transfer Learning

Al-Othni, Asma

Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images; however, critical questions remain regarding how quantum principles might best enhance their representational capacity. This thesis investigates hybrid quantum-classical GAN architectures supplemented by transfer learning in the discriminator, systematically examining whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over fully classical baselines. We evaluate each configuration using standard GAN benchmarks (CIFAR-10 classes: Birds, Cars, and Dogs) under varying sample sizes (5,000 vs. 2,500 images per class) to gauge both robustness and data efficiency. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, consistently produce images of higher visual quality and achieve more favorable quantitative metrics (such as Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Inception Score (IS)) compared to their fully classical counterpart. In particular, VQCs in the generator accelerate early feature learning, whereas those in the discriminator, despite exhibiting slower initial convergence, ultimately facilitate more refined synthetic outputs. Moreover, the model sustains near-comparable performance even when the dataset size is halved, suggesting that transfer learning and quantum enhancements mitigate data limitations. By comparing classical and hybrid configurations in detail, this thesis illustrates the trade-offs arising from VQCs in GANs, such as variations in early-epoch convergence and final generative quality. Overall, the results underscore that carefully integrating quantum computing principles with classical adversarial training and pretrained feature extraction can significantly enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.

•Jan 1, 2025•0 citations

QuCon-GAN: A Parameter-Efficient Quantum-Classical Conditional GAN for Handwritten Digit Generation

Xiaoping Lou, Chengzeng Long, L C WANG +1 more

The development of compact and controllable generative models under resource constraints remains a critical challenge for the practical deployment of conditional generative adversarial networks (cGANs). In this work, QuCon-GAN, a hybrid quantum-classical conditional GAN, is proposed to enhance generation expressiveness while drastically reducing parameter counts. Within the generator, dynamic data re-upload, parameterized unitary transformations, and adaptive entanglement have been incorporated into a variational quantum circuit, thereby enabling continuous semantic guidance and feature refinement across layers. When compared to classical counterparts, QuCon-GAN achieves significant improvements in parameter efficiency and conditional control, supporting full-category generation on the MNIST dataset at a resolution of 32×32 pixels. Extensive experiments have demonstrated that QuCon-GAN attains a Fréchet Inception Distance (FID) of 52.42, while maintaining stable adversarial training and avoiding mode collapse even under limited quantum resources (8 qubits). Furthermore, systematic comparisons against classical baselines and recent quantum GANs have validated the effectiveness of QuCon-GAN in balancing resource efficiency, stability, and semantic controllability. This work demonstrates the potential of hybrid quantum-classical architectures for advancing lightweight generative modeling in the Noisy Intermediate-Scale Quantum (NISQ) era.

IEEE Transactions on Consumer Electronics•Jan 1, 2026•0 citations
Abstract Quantum machine learning (QML) has garnered significant attention for its potential to outperform classical machine learning.A notable area within QML is quantum generative adversarial networks (QGANs), which serve as the quantum equivalent to classical GANs, commonly used in image processing and generation.However, the content of images generated by existing QGANs is still uncontrollable.In this work, we introduce a conditional encoder for the quantum generator, enabling it to controllably produce multiple image types.While this approach can, in principle, be extended to any number of conditional generations, its practical applicability is limited by the finite qubit resources available.Our results show that it can generate images of satisfactory quality, with a Frechet Inception Distance (FID) score of 201.6201.6201.6, a Kernel Inception Distance (KID) score of 0.2810.2810.281, and a Learned Perceptual Image Patch Similarity (LPIPS) score of 0.4610.4610.461.Through quantum noise experiments, we show that when the noise intensity reaches 0.20.20.2, the relative changes in FID, KID, and LPIPS remain below 5%5\%5%, indicating that the model is robust to moderate noise levels.Furthermore, in comparative experiments against without multicondition or limitted multicondition, our method outperforms the strongest baseline by 3%−11%3\%-11\%3%−11% , thereby demonstrating its stable superiority over current approaches.
With the speedy advancement of hardware, quantum machine learning has garnered widespread attention. Generative Adversarial Networks (GANs) are widely adopted quantum machine learning frameworks used for providing highstandard audio content, images, and videos. Utilizing quantum computing for image generation has been found to offer several potential advantages over non-quantum technologies. Current quantum Generative Adversarial Networks (QGANs) still face challenges, such as the inability to generate high-quality images. In the current investigation, we propose a QGAN model based on Autoencoders (BAE-QCGAN) and evaluate its performance. By drawing upon the entanglement and expression capabilities of quantum circuits, our composite system outperforms classical GANs in terms of Frechet Inception Distance, requiring fewer training parameters and fewer iterations to converge. We also demonstrate that BAEQCGAN outperforms another quantum GAN, the patch-GAN, and is adapted for existing Noisy Intermediate Scale Quantum (NISQ) computers.
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), as a rising paradigm in Quantum Machine Learning, have shown promising potential in image generation and processing. However, their output quality remains suboptimal, and existing research is largely limited to small-scale, proof-of-concept studies. In this work, we propose a hybrid quantum-classical GAN architecture, where the generator integrates parameterized quantum circuits (PQCs) and classical neural networks. This integration significantly enhances the visual quality of generated images. Our model leverages the complementary strengths of quantum and classical components and outperforms existing methods (Tsang et al. in IEEE Trans. Quantum Eng. 4:1–19, 2023 ; Gulrajani et al. in Proceedings of the 31st international conference on neural information processing systems. NIPS’17, Red Hook, pp. 5769–5779, 2017 ), particularly in terms of image fidelity. Experiments conducted on the MNIST family of datasets show that our hybrid approach achieves a 20.26% average reduction in Fréchet Inception Distance. Furthermore, it improves the Structural Similarity Index Measure, Cosine Similarity, and Peak Signal-to-Noise Ratio by 26.04%, 2.22%, and 7.62%, respectively. These results highlight the effectiveness of combining quantum computing with machine learning, and underscore the potential of hybrid quantum-classical models in advancing generative tasks.
Abstract Quantum generative adversarial networks (QGANs) have demonstrated strong capabilities in tasks like synthetic data generation and detecting anomalies. Recent developments have increasingly integrated traditional machine learning techniques to boost the performance of QGANs. Motivated by this progress, we propose an innovative QGAN architecture that incorporates a classical learning component and employs a dual-generator design. Our approach improves upon the traditional hybrid quantum–classical GAN structure and introduces a redesigned loss function tailored for the new model. Experiments on multiple datasets indicate that our method surpasses previous techniques in image generation quality, achieving a 1.38% average reduction in Fréchet inception distance scores compared to the current state-of-the-art, and improvements of 6.52%, 0.36%, and 0.38% in structural similarity index, cosine similarity, and peak signal-to-noise ratio metrics, respectively. Additionally, our architecture supports the generation of larger images (up to 78 × 78 ), as verified on the CelebA dataset. Simulations conducted in noisy conditions further confirm the robustness and effectiveness of both the proposed architecture and loss function.
Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images; however, critical questions remain regarding how quantum principles might best enhance their representational capacity. This thesis investigates hybrid quantum-classical GAN architectures supplemented by transfer learning in the discriminator, systematically examining whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over fully classical baselines. We evaluate each configuration using standard GAN benchmarks (CIFAR-10 classes: Birds, Cars, and Dogs) under varying sample sizes (5,000 vs. 2,500 images per class) to gauge both robustness and data efficiency. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, consistently produce images of higher visual quality and achieve more favorable quantitative metrics (such as Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Inception Score (IS)) compared to their fully classical counterpart. In particular, VQCs in the generator accelerate early feature learning, whereas those in the discriminator, despite exhibiting slower initial convergence, ultimately facilitate more refined synthetic outputs. Moreover, the model sustains near-comparable performance even when the dataset size is halved, suggesting that transfer learning and quantum enhancements mitigate data limitations. By comparing classical and hybrid configurations in detail, this thesis illustrates the trade-offs arising from VQCs in GANs, such as variations in early-epoch convergence and final generative quality. Overall, the results underscore that carefully integrating quantum computing principles with classical adversarial training and pretrained feature extraction can significantly enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.
The development of compact and controllable generative models under resource constraints remains a critical challenge for the practical deployment of conditional generative adversarial networks (cGANs). In this work, QuCon-GAN, a hybrid quantum-classical conditional GAN, is proposed to enhance generation expressiveness while drastically reducing parameter counts. Within the generator, dynamic data re-upload, parameterized unitary transformations, and adaptive entanglement have been incorporated into a variational quantum circuit, thereby enabling continuous semantic guidance and feature refinement across layers. When compared to classical counterparts, QuCon-GAN achieves significant improvements in parameter efficiency and conditional control, supporting full-category generation on the MNIST dataset at a resolution of 32×32 pixels. Extensive experiments have demonstrated that QuCon-GAN attains a Fréchet Inception Distance (FID) of 52.42, while maintaining stable adversarial training and avoiding mode collapse even under limited quantum resources (8 qubits). Furthermore, systematic comparisons against classical baselines and recent quantum GANs have validated the effectiveness of QuCon-GAN in balancing resource efficiency, stability, and semantic controllability. This work demonstrates the potential of hybrid quantum-classical architectures for advancing lightweight generative modeling in the Noisy Intermediate-Scale Quantum (NISQ) era.