Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation
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.
Related
- Fully passive monolithic silicon quantum photonic circuit for entangled photon-pair generation
- Spatially resolved system-level calibration for high-fidelity complex-amplitude modulation using a phase-only spatial light modulator
- Data and code for collision-model Dicke-state preparation: depth-fidelity frontiers, circuit costs, and superconducting-processor measurements
- Quickly extracting fidelity decay rates in random circuit benchmarking experiments
- FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration
BibTeX
@misc{yang2026quantum,
title = {{Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation}},
author = {Xue Yang and Rigui Zhou and Dax Enshan Koh and Siong Thye Goh and Yitao Tang and ShiZheng Jia and Young-Wook Cho and Hongyu Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36702},
eprint = {2609.36702},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36702},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation
AU - Xue Yang
AU - Rigui Zhou
AU - Dax Enshan Koh
AU - Siong Thye Goh
AU - Yitao Tang
AU - ShiZheng Jia
AU - Young-Wook Cho
AU - Hongyu Chen
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36702
UR - https://arxiv.org/abs/2609.36702
AB - 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.
ER -