Search papers, labs, and topics across Lattice.
The paper introduces ReQGAN, an end-to-end Quantum Generative Adversarial Network for direct full-image synthesis using a D-qubit quantum circuit to generate N=2^D pixels. ReQGAN addresses the limitations of previous QGANs by incorporating a learnable Neural Noise Encoder to improve the classical-to-quantum noise interface and a differentiable Intensity Calibration module to align quantum measurements with pixel intensities. Experiments on MNIST and Fashion-MNIST show ReQGAN's ability to achieve stable training and effective image synthesis with limited qubits.
End-to-end quantum image generation is now possible, even with limited qubits, thanks to a new method that bridges the gap between quantum circuits and pixel intensities.
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.
