发表机构
Shandong Police College; Ocean University of China（山东警察学院; 中国海洋大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出上下文感知互学习（CAML）框架，联合掩码估计与图像修复，通过双向上下文互学习提升盲图像修复性能，并在去雪、去阴影和去水印等任务上达到最先进水平。
AI 中文摘要
盲图像修复旨在未知掩码的情况下恢复受污染的图像，是一项具有挑战性的任务。受人类视觉和知识视角的启发，盲图像修复可以分解为两个阶段：掩码估计和基于估计掩码的图像修复。与单阶段方案相比，两阶段思想通过显式利用估计的掩码进行图像修复，在提升修复质量和增强对未知真实世界污染的泛化能力方面展现出明显优势。这一两阶段思想也已被直观地实现。然而，现有的两阶段方法过度强调掩码估计对图像修复的单向关系，可能忽略它们之间的相互关系。具体而言，掩码估计可以为图像修复提供更多上下文语义以增强对语义的理解，而图像修复可以为掩码估计提供更多上下文细节（如纹理和边缘）以改善细节的学习。在这项工作中，我们提出了一种新颖的上下文感知互学习（CAML）框架用于盲图像修复，该框架联合掩码估计和图像修复以相互利用上下文信息。在CAML框架中，我们设计了修复引导的上下文互学习（IGCM）学习器，从图像修复中获取互补的上下文细节以辅助掩码估计，以及估计引导的上下文互学习（EGCM）学习器，从掩码估计中增强对上下文语义的理解以辅助图像修复。消融研究验证了我们CAML的有效性。大量实验表明，我们的CAML在盲图像修复以及额外的视觉任务（即去雪、去阴影和去水印）上均达到了最先进的性能，显示了其优越性。
英文摘要
Blind image inpainting, aiming to recover contaminated images in the case of unknown masks, is a challenging task. Motivated by the perspective of human vision and knowledge, blind image inpainting can be decomposed into two stages: mask estimation and image inpainting based on the estimated mask. The two-stage idea exhibits evident advantages in enhancing inpainting quality and augmenting the generalization capability of unknown real-world contamination by explicitly employing the estimated mask for image inpainting compared to one-stage scheme. This two-stage idea has also been intuitively implemented. However, existing two-stage methods excessively emphasize the unilateral relationship of mask estimation to image inpainting, and may overlook the mutual relations between them. Specifically, mask estimation can provide more contextual semantics for image inpainting to strengthen the understanding of semantics, and image inpainting can offer more contextual details (e.g., textures and edges) for mask estimation to improve the learning of details. In this work, we propose a novel Context-Aware Mutual Learning (CAML) framework for blind image inpainting that joints mask estimation and image inpainting to mutually exploit contextual information. In the CAML framework, we design the Inpainting-Guided Context-Mutual (IGCM) learner to acquire the complementary contextual details from image inpainting for assisting mask estimation, and the Estimation-Guided Context-Mutual (EGCM) learner to strengthen the understanding of contextual semantics from mask estimation for assisting image inpainting. Ablation studies validate the efficacy of our CAML. Extensive experiments show that our CAML achieves state-of-the-art performance on both blind image inpainting and additional vision tasks, i.e., snow removal, shadow removal, and watermark removal, indicating its superiority.
CommentsPublished in Expert Systems with Applications 268 (2025), Article 126224
Journal refExpert Systems with Applications 268 (2025), Article 126224
DOI：10.1016/j.eswa.2024.126224
