首个针对物理科学逆问题的扩散模型评估基准，验证其在多个真实场景中的表现。
InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
- 构建跨五类科学逆问题的统一评估框架，涵盖光学断层成像等真实应用。
- 对比14种基于扩散模型的算法与领域专用基线，发现性能差异显著。
- 开源数据集、代码和预训练模型，推动物理科学中逆问题研究发展。
插件式扩散先验（PnPDP）在解决逆问题方面展现出巨大潜力，但现有研究多集中于自然图像修复，缺乏对科学领域逆问题性能的系统评估。为此，我们提出 extsc{InverseBench}，一个面向五个不同科学逆问题的基准测试框架，包括光学断层成像、医学成像、黑洞成像、地震学和流体动力学等关键应用场景。这些任务具有独特结构挑战，区别于传统图像基准。通过 extsc{InverseBench}，我们对14种使用插件式扩散先验的算法与强域特定基线进行对比，揭示了现有方法的优势与局限。为促进后续研究，我们开源了代码库、数据集及预训练模型，详见 https://devzhk.github.io/InverseBench/。
原文摘要 · Abstract (English)
Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies primarily focus on natural image restoration, leaving the performance of these algorithms in scientific inverse problems largely unexplored. To address this gap, we introduce \textsc{InverseBench}, a framework that evaluates diffusion models across five distinct scientific inverse problems. These problems present unique structural challenges that differ from existing benchmarks, arising from critical scientific applications such as optical tomography, medical imaging, black hole imaging, seismology, and fluid dynamics. With \textsc{InverseBench}, we benchmark 14 inverse problem algorithms that use plug-and-play diffusion priors against strong, domain-specific baselines, offering valuable new insights into the strengths and weaknesses of existing algorithms. To facilitate further research and development, we open-source the codebase, along with datasets and pre-trained models, at https://devzhk.github.io/InverseBench/.
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。