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

TL;DR

ReQGAN is an innovative quantum generative adversarial network that enables end-to-end, full-image synthesis on near-term quantum devices by using neural noise encoding and intensity calibration, overcoming previous limitations.

Contribution

This work introduces ReQGAN, the first framework for direct full-image synthesis with a single D-qubit quantum circuit, addressing key bottlenecks in quantum image generation.

Findings

Achieves stable training on MNIST and Fashion-MNIST.

Effectively synthesizes images with limited qubits.

Ablation studies confirm component effectiveness.

Abstract

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.