English

DEALing with Image Reconstruction: Deep Attentive Least Squares

Image and Video Processing 2025-02-07 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-28T21:34:48.837Z