用于引导深度图超分辨率的双图正则化深度展开网络
Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolution
把图优化展开成可解释的多阶段网络，并用行列分离的双图拉普拉斯先验把复杂度从 O(H^3W^3) 降到 O(H^3+W^3)，这套「先验建模+展开求解」的范式可直接迁移到其他需要结构保持的复原任务（如引导滤波式上采样、联合滤波）。
原文依据 we propose a novel GDSR framework based on a dual graph Laplacian prior, termed LapNet, which efficiently unfolds graph optimization into a deep neural network
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论带颜色引导的深度图超分辨率是计算机视觉中的一项基础任务，旨在利用对应引导图像中的结构相关性重建高分辨率深度图。近年来，随着深度学习技术的发展，引导深度超分辨率（GDSR）模型的性能得到了显著提升。然而，大多数现有方法依赖缺乏理论可解释性的黑盒架构。尽管已有研究探索将图优化用于融合模型驱动与数据驱动的框架，但其计算代价高昂，且难以保持深度图的固有结构。为克服这些局限，我们提出了一种基于双图拉普拉斯先验的新型 GDSR 框架，称为 LapNet，它将图优化高效地展开为深度神经网络。具体而言，我们首先构建一种双图拉普拉斯先验，分别对深度图行方向和列方向上的结构依赖关系进行建模。该形式显式地施加分段平滑性，并通过避免构建全局亲和图，将计算复杂度从 O(H^3W^3) 降至 O(H^3 + W^3)。此外，我们设计了一种深度隐式先验，从引导图像中提取高频结构线索，作为人工设计先验的补充成分。最后，我们将这些互补先验整合到一个统一的变分优化框架中，通过交替最小化高效求解，并随后展开为可解释的多阶段深度网络。在合成数据集和真实数据集上的大量实验表明，LapNet 在保持低计算复杂度的同时达到了最优性能。
英文原文摘要 1813 字符
Depth map super-resolution with color guidance is a fundamental task in computer vision that aims to reconstruct high-resolution depth maps by leveraging structural correlations from corresponding guidance images. Recently, with the development of deep learning techniques, the performance of guided depth super-resolution (GDSR) models has been significantly improved. However, most existing approaches rely on black-box architectures that lack theoretical interpretability. Although graph optimization has been explored to integrate model-driven and data-driven frameworks, it remains computationally expensive and struggles to preserve the intrinsic structures of the depth maps. To overcome these limitations, we propose a novel GDSR framework based on a dual graph Laplacian prior, termed LapNet, which efficiently unfolds graph optimization into a deep neural network. Specifically, we first formulate a dual graph Laplacian prior that separately models structural dependencies along the row and column dimensions of the depth maps. This formulation explicitly enforces piecewise smoothness while reducing computational complexity from O(H^3W^3) to O(H^3 + W^3) by avoiding the construction of global affinity graph. Furthermore, we develop a deep implicit prior to extract high-frequency structural cues from the guidance image, serving as a complementary component to the manually designed prior. Finally, we integrate these complementary priors into a unified variational optimization framework, which is efficiently solved through alternating minimization and subsequently unfolded into an interpretable multi-stage deep network. Extensive experiments on both synthetic and real-world datasets demonstrate that LapNet achieves state-of-the-art performance while maintaining low computational complexity.