Quantum fidelity calibration improves single-circuit QGAN image generation
Quantum Fidelity Landscape-Guided Prior Calibration for Single-Circuit QGAN Image Generation
Computer Vision and Pattern Recognition
Summary
Generating images directly on quantum computers is challenging due to noise and complexity. The authors study a method to make quantum image generation more stable and efficient by adjusting the quantum starting point before training. They introduce a way to measure how similar quantum states are to guide this adjustment, which helps produce better images using fewer quantum resources. Their approach, called BasicQGAN, works well on simple grayscale images and uses less computational power than earlier methods.
What this means in practice
- •For quantum algorithm developers: Optimize quantum generative models to produce pixel-level images efficiently with fewer qubits by calibrating initial quantum states before training.
- •For quantum hardware engineers: Design quantum circuits with prior fidelity alignment to improve stability and reduce resource overhead in image generation tasks.
Authors
Xue Yang, Rigui Zhou, Dax Enshan Koh, Siong Thye Goh, Yitao Tang, ShiZheng Jia, Young-Wook Cho, Hongyu Chen
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.