Abstract
In medical imaging, generative models are increasingly relied upon for two distinct but equally critical tasks: reconstruction, where the goal is to restore medical imaging (usually inverse problems like inpainting or superresolution), and generation, where synthetic data is created to augment datasets or carry out counterfactual analysis. Despite shared architecture and learning frameworks, they prioritize different goals: generation seeks high perceptual quality and diversity, while reconstruction focuses on data fidelity and faithfulness. In this work, we introduce a "generative model zoo" and systematically analyze how modern latent diffusion models and autoregressive models navigate the reconstruction-generation spectrum. We benchmark a suite of generative models across representative cardiac medical imaging tasks, focusing on image inpainting with varying masking ratios and sampling strategies, as well as unconditional image generation. Our findings show that diffusion models offer superior perceptual quality for unconditional generation but tend to hallucinate as masking ratios increase, whereas autoregressive models maintain stable perceptual performance across masking levels, albeit with generally lower fidelity.
Abstract (translated)
在医学影像领域，生成模型越来越被用于两种不同但同样重要的任务：重建和生成。在重建任务中，目标是恢复医学影像（通常涉及逆问题如图像插值或超分辨率），而在生成任务中，则是为了创建合成数据以扩充数据集或进行反事实分析。尽管这些模型共享相似的架构和学习框架，但在优先目标上有所不同：生成任务追求高质量且多样化的视觉效果，而重建则侧重于数据的真实性和准确性。在这项工作中，我们引入了一个“生成模型动物园”，并系统地分析了现代潜在扩散模型和自回归模型在重建与生成之间的表现差异。我们在代表性的心脏医学影像任务中对一系列生成模型进行了基准测试，重点关注不同遮挡比例下的图像插值及无条件的图像生成。我们的研究结果表明，扩散模型在无条件生成方面提供了更好的视觉质量，但在遮挡比例增加时容易产生幻觉；而自回归模型则在整个遮挡级别上保持稳定的视觉性能，尽管其总体真实度较低。
URL
https://arxiv.org/abs/2507.19186
