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.
@article{arxiv.2502.04079,
title = {DEALing with Image Reconstruction: Deep Attentive Least Squares},
author = {Mehrsa Pourya and Erich Kobler and Michael Unser and Sebastian Neumayer},
journal= {arXiv preprint arXiv:2502.04079},
year = {2025}
}