State-of-the-art image reconstruction often relies on complex, highly parameterized deep architectures. We propose an alternative: a data-driven reconstruction method inspired by the classic Tikhonov regularization. Our approach iteratively refines intermediate reconstructions by solving a sequence of quadratic problems. These updates have two key components: (i) learned filters to extract salient image features, and (ii) an attention mechanism that locally adjusts the penalty of filter responses. Our method achieves performance on par with leading plug-and-play and learned regularizer approaches while offering interpretability, robustness, and convergent behavior. In effect, we bridge traditional regularization and deep learning with a principled reconstruction approach.

翻译：当前最先进的图像重建方法通常依赖于复杂且高度参数化的深度架构。我们提出一种替代方案：一种受经典Tikhonov正则化启发的数据驱动重建方法。该方法通过求解一系列二次优化问题来迭代优化中间重建结果。这些更新包含两个关键组成部分：(i) 用于提取显著图像特征的学习滤波器，以及(ii) 通过注意力机制局部调整滤波器响应惩罚项。本方法在保持与主流即插即用及学习型正则化方法相当性能的同时，兼具可解释性、鲁棒性和收敛特性。实际上，我们通过一种原理性重建框架，在传统正则化方法与深度学习之间建立了桥梁。