发表机构
Université Paris Cité; CNRS; Heriot-Watt University; Maxwell Institute for Mathematical Sciences（巴黎西岱大学; 法国国家科学研究中心; 赫瑞-瓦特大学; 麦克斯韦数学科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出BAM，一种轻量级物理感知基础模型，通过条件流映射实现少步后验采样，仅36M参数，在多个线性逆问题基准上以3步超越专用模型和零样本方法，降低计算成本。
AI 中文摘要
生成式模型正在变革贝叶斯计算成像，但该领域仍缺乏物理感知的基础模型。当前实践分为两大阵营。大型基础图像模型作为即插即用的先验，配合零样本近似似然引导，这引入了显著的偏差和计算成本。物理感知的生成式模型避免了这种偏差，但每个模型都绑定于特定的数据集、任务和仪器。我们提出了BAM（贝叶斯任意模型），一个轻量级基础模型，用于少步、物理感知的后验采样，能够稳健地泛化到未见过的数据和任务，无论是零样本还是只需极少的微调。BAM将基于算子条件的“重建任意模型”（RAM）骨干网络（Terris等人）升级为条件流映射，使得仪器物理特性在推理时指定，而非在训练时固定。BAM仅拥有3600万个参数，并在大型图像语料库和前向算子库上联合预训练。单个网络即可在几步内抽取后验样本，无需似然近似，也无需调整引导权重。在FFHQ、AFHQ、LSUN、DIV2K和Kohler相机抖动基准上的线性逆问题中，BAM仅用3步就在样本质量上超越了专门的模型和领先的零样本方法，而其计算成本仅为其一小部分。BAM为社区提供了一个进入生成式计算成像的便捷入口，降低了训练成像模型的经济和环境成本，并为物理感知的贝叶斯计算成像研究开辟了新路径。官方页面：此https URL
英文摘要
Generative models are transforming Bayesian computational imaging, yet the field still lacks physics-aware foundation models. Current practice falls into two camps. Large foundation image models are deployed as plug-and-play priors with zero-shot approximate likelihood guidance, which introduces significant bias and computational cost. Physics-aware generative models avoid this bias, but each is tied to a specific dataset, task and instrument. We introduce BAM (Bayesian Anything Model), a lightweight foundation model for few-step, physics-aware posterior sampling that generalises robustly to unseen data and tasks, zero-shot or with minimal finetuning. BAM upgrades the operator-conditioned Reconstruct Anything Model (RAM) backbone (Terris et al.) into a conditional flow map, so instrument physics is specified at inference time rather than fixed during training. BAM has just 36M parameters and is pre-trained jointly on large image corpora and libraries of forward operators. A single network then draws posterior samples in a few steps, with no likelihood approximation and no guidance weights to tune. Across linear inverse problems on FFHQ, AFHQ, LSUN, DIV2K and the Kohler camera-shake benchmark, BAM outperforms in just 3 steps both specialised models and leading zero-shot methods in sample quality, at a fraction of their computational cost. BAM gives the community an accessible entry point to generative computational imaging, lowers the economic and environmental cost of training imaging models, and opens a new path for research on physics-aware Bayesian computational imaging. Official page: https://bayesian-anything-model.github.io/
Comments37 pages, 25 figures
