DEALing with Image Reconstruction: Deep Attentive Least Squares
This work addresses image reconstruction for applications requiring interpretable and robust methods, though it is incremental in bridging traditional regularization with deep learning.
The paper tackles image reconstruction by proposing a data-driven method inspired by Tikhonov regularization, achieving performance on par with leading approaches while offering interpretability, robustness, and convergent behavior.
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.