发表机构
ECE School, Ben-Gurion University of the Negev; Nuclear Research Center Negev（内盖夫本-古里安大学电气与计算机工程学院; 内盖夫核研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对泊松图像重建中MLEM需多轮迭代且对模型失配敏感的问题，提出深度展开惩罚型MLEM框架，通过少量可训练层结合数据依赖校正，在固定迭代预算下提升了重建分辨率与质量。
AI 中文摘要
最大似然期望最大化（MLEM）是泊松图像重建的常用方法，但准确恢复图像需要多次迭代，且对假设采集模型的失配敏感。我们提出深度展开惩罚型MLEM框架，将规定的少量迭代映射为可训练层，同时保留MLEM的解析正/反向投影及乘法结构。该展开架构学习层相关正则化项与泊松模型参数，还对灵敏度归一化进行数据依赖校正以缓解模型失配。数值实验表明，在固定迭代预算下，我们的方法可提升重建分辨率，且重建质量可与长迭代MLEM运行及直接数据驱动模型相当。
英文摘要
Maximum likelihood expectation maximization (MLEM) is a common approach for Poisson image reconstruction, but accurate recovery requires many iterations and is sensitive to mismatch in the assumed acquisition model. We propose a deep-unfolded penalized MLEM framework that maps a prescribed small number of iterations into trainable layers while retaining the analytical forward/backward projections and the multiplicative structure of MLEM. The unfolded architecture learns layer-dependent regularization and Poisson-model parameters, together with a data-dependent correction of the sensitivity normalization to mitigate model mismatch. We numerically show that our method improves reconstruction resolution at a fixed iteration budget and attains reconstruction quality comparable to long MLEM runs and direct data-driven models.
Comments5 pages, 4 figures. Submitted to IEEE ICASSP 2027 (under review)
