用可解释的深度方法实现图像重建，性能媲美顶尖模型。
DEALing with Image Reconstruction: Deep Attentive Least Squares
- 基于经典正则化思想，迭代求解二次优化问题
- 融合学习滤波器与注意力机制，提升重建质量
- 兼具可解释性、鲁棒性，适合追求可信重建的场景
当前最先进的图像重建方法通常依赖复杂且参数量大的深度架构。本文提出一种替代方案：受经典Tikhonov正则化启发的数据驱动重建方法。该方法通过迭代求解一系列二次优化问题，逐步精炼中间重建结果。更新过程包含两个关键组件：(i) 学习得到的滤波器用于提取图像显著特征，(ii) 注意力机制对滤波器响应进行局部惩罚调整。所提方法在性能上达到领先插件式及学习型正则化方法的水平，同时具备可解释性、鲁棒性与收敛性。本质上，本工作以合理框架连接了传统正则化与深度学习，提供了一种可信赖的重建范式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。