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

2026-09-29

AI Summary

This study addresses the limitations of existing quantum generative adversarial networks (QGANs), which rely on patch-wise decomposition and consequently suffer from weak global consistency and high quantum resource overhead. To overcome these challenges, this work proposes a single-circuit, end-to-end, pixel-level generation method. By introducing quantum fidelity landscape theory, the approach reveals the structural correspondence between prior and data distributions, thereby guiding prior calibration to optimize training dynamics. Experimental results demonstrate that the proposed model achieves stable and efficient pixel-level image generation using an extremely small number of qubits and parameters. Furthermore, it significantly outperforms representative patch-based quantum generators in overall performance.

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.

Problem

• Quantum Generative Adversarial Networks
• Single-circuit QGAN
• End-to-end image generation
• Patch-based decomposition
• Quantum resource overhead

Innovation

• Quantum Fidelity Landscape
• Single-Circuit QGAN
• Prior Calibration
• End-to-End Image Generation
• BasicQGAN