用量子-经典混合架构提升图像生成质量，避免模式崩溃。
Enhancing Quantum Diffusion Models for Complex Image Generation
- 结合量子潜空间与可训练观测算子，捕捉非局部特征。
- 在完整MNIST数据集上实现所有数字类的结构连贯生成。
- 适合对量子机器学习和生成模型感兴趣的科研人员。
量子生成模型为探索高维希尔伯特空间提供了新路径，但在处理多模态分布时面临可扩展性和表达能力的挑战。本文提出一种融合自适应非局部观测算子（ANO）的混合量子-经典U-Net架构，通过将经典数据压缩至密集量子潜空间，并利用可训练观测算子提取非局部特征以补充经典处理。同时研究了跳跃连接在反向扩散过程中保持语义信息的作用。在完整MNIST数据集（0-9数字）上的实验表明，该架构能生成所有数字类别结构连贯且可识别的图像。尽管硬件限制仍影响图像分辨率，结果表明带有自适应测量的混合架构为缓解模式崩溃、增强生成能力提供了可行方案，适用于当前的近似量子计算时代（NISQ era）。
原文摘要 · Abstract (English)
Quantum generative models offer a novel approach to exploring high-dimensional Hilbert spaces but face significant challenges in scalability and expressibility when applied to multi-modal distributions. In this study, we explore a Hybrid Quantum-Classical U-Net architecture integrated with Adaptive Non-Local Observables (ANO) as a potential solution to these hurdles. By compressing classical data into a dense quantum latent space and utilizing trainable observables, our model aims to extract non-local features that complement classical processing. We also investigate the role of Skip Connections in preserving semantic information during the reverse diffusion process. Experimental results on the full MNIST dataset (digits 0-9) demonstrate that the proposed architecture is capable of generating structurally coherent and recognizable images for all digit classes. While hardware constraints still impose limitations on resolution, our findings suggest that hybrid architectures with adaptive measurements provide a feasible pathway for mitigating mode collapse and enhancing generative capabilities in the NISQ era.
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。