用量子电路直接生成完整图像，突破传统方法限制。
End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration
- 设计可学习的神经噪声编码器与可微强度校准模块
- 在仅20个量子比特下实现稳定训练并生成清晰图像
- 适合量子机器学习、图像生成方向研究者参考
量子生成对抗网络（QGAN）为在近中期量子设备上学习数据分布提供了前景。然而，现有用于图像合成的QGAN通常避免直接生成整幅图像，依赖经典后处理或基于图像块的方法，削弱了量子生成器的作用，并难以捕捉全局语义。为此，我们提出ReQGAN，一种端到端框架，利用单个D量子比特电路生成包含N=2^D个像素的完整图像。ReQGAN克服两大关键瓶颈：(1) 固定的经典-量子噪声接口；(2) 量子测量统计与期望像素强度空间不匹配。我们引入可学习的神经噪声编码器实现自适应态制备，以及可微的强度校准模块，将测量结果映射至稳定且视觉有意义的像素域。在MNIST和Fashion-MNIST上的实验表明，ReQGAN在严格量子比特预算下实现稳定训练与有效图像合成，消融实验证明各组件贡献显著。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。