发表机构
Univ. Grenoble Alpes; Inria; CNRS; Grenoble INP; LJK（格勒诺布尔阿尔卑斯大学; 法国国家信息与自动化研究所; 法国国家科学研究中心; 格勒诺布尔理工学院; 计算几何与知识实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对非配对数据逆问题，提出在干净侧增加分布匹配以约束前向算子估计，通过可微即插即用算法实现，在空间变化PSF标定和盲超分辨率中提升算子恢复精度。
AI 中文摘要
从非配对数据中恢复成像系统的前向算子，既避免了校准硬件的需求，也无需监督学习所需的干净/退化图像对——对于真实镜头而言，这类图像对往往难以获取。现有的非配对方法通过分布匹配显式估计前向算子，仅通过其生成的测量值来评估候选算子，要求这些测量值的分布与真实测量值分布相匹配。被算子抑制的成分在退化图像中几乎不存在，因此在该准则下几乎无法约束算子。然而，逆问题恰恰试图恢复这些成分。结果，两个作为前向模型几乎无法区分的算子，其逆过程可能差异巨大。我们通过增加干净侧的对比来解决这一问题：真实退化图像经恢复后，其分布应与干净图像分布一致。恢复过程由可微的即插即用算法计算，该算法由正在学习的算子参数化。在空间变化的点扩散函数标定和盲超分辨率任务中，该方法恢复的算子比仅依赖退化侧匹配的方法更准确，并大幅缩小了与使用真实算子进行恢复之间的差距。
英文摘要
Recovering the forward operator of an imaging system from unpaired data avoids both calibration hardware and the clean/degraded pairs that supervision requires-pairs that, for a real lens, are often impossible to acquire. Existing unpaired approaches that explicitly estimate the forward operator by distribution matching evaluate a candidate only through the measurements it generates, whose distribution should match that of the real ones. Components suppressed by the operator are barely present in the degraded images, and therefore barely constrain the operator under such a criterion. Yet inversion precisely tries to recover them. As a result, two operators that are nearly indistinguishable as forward models can invert very differently. We address this by adding a comparison on the clean side: real degraded images, once restored, should be distributed like clean ones. Restorations are computed by a differentiable plug-and-play algorithm parameterized by the operator being learned. On spatially varying PSF calibration and blind super-resolution, the method recovers more accurate operators than degraded-side matching alone, and closes much of the gap to restoration with the true operator.
