Visual restoration of underwater scenes is crucial for visual tasks, and avoiding interference from underwater media has become a prominent concern. In this work, we present a synergistic multiscale detail refinement via intrinsic supervision (SMDR-IS) to recover underwater scene details. The low-degradation stage provides multiscale detail for original stage, which achieves synergistic multiscale detail refinement through feature propagation via the adaptive selective intrinsic supervised feature module (ASISF), which achieves synergistic multiscale detail refinement. ASISF is developed using intrinsic supervision to precisely control and guide feature transmission in the multi-degradation stages. ASISF improves the multiscale detail refinement while reducing interference from irrelevant scene information from the low-degradation stage. Additionally, within the multi-degradation encoder-decoder of SMDR-IS, we introduce a bifocal intrinsic-context attention module (BICA). This module is designed to effectively leverage multi-scale scene information found in images, using intrinsic supervision principles as its foundation. BICA facilitates the guidance of higher-resolution spaces by leveraging lower-resolution spaces, considering the significant dependency of underwater image restoration on spatial contextual relationships. During the training process, the network gains advantages from the integration of a multi-degradation loss function. This function serves as a constraint, enabling the network to effectively exploit information across various scales. When compared with state-of-the-art methods, SMDR-IS demonstrates its outstanding performance. Code will be made publicly available.

翻译：水下场景的视觉恢复对视觉任务至关重要，如何避免水下介质的干扰已成为重要关注点。本文提出一种基于内在监督的协同多尺度细节细化方法（SMDR-IS），用于恢复水下场景细节。低退化阶段为原始阶段提供多尺度细节，通过自适应选择性内在监督特征模块（ASISF）的特征传播实现协同多尺度细节细化。ASISF利用内在监督精确控制和引导多退化阶段的特征传输，在增强多尺度细节细化的同时减少低退化阶段中无关场景信息的干扰。此外，在SMDR-IS的多退化编码器-解码器中，我们引入双焦距内在上下文注意力模块（BICA）。该模块以内在监督原理为基础，旨在有效利用图像中的多尺度场景信息。考虑到水下图像恢复对空间上下文关系的显著依赖性，BICA通过利用低分辨率空间引导高分辨率空间。在训练过程中，网络通过整合多退化损失函数获得优势，该函数作为约束条件使网络能够有效利用多尺度信息。与现有最优方法相比，SMDR-IS展现出卓越性能。代码将公开提供。