发表机构
College of Future Information Technology, Fudan University; Institute of Artificial Intelligence (TeleAI), China Telecom; Faculty of Robot Science and Engineering, Northeastern University; School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（复旦大学未来信息技术学院; 中国电信人工智能研究院（TeleAI）; 东北大学机器人科学与工程学院; 西北工业大学人工智能与光学电子学院（iOPEN））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对水下图像增强的语义漂移问题，提出RPL-UIE两阶段教师-学生框架，结合RPRD与FPRD缩小师生模型先验学习差异，在基准测试、下游视觉任务及真实ROV数据上表现良好。
AI 中文摘要
水下图像增强（UIE）旨在从受波长相关吸收、散射及空间非均匀退化影响的观测数据中恢复清晰图像。尽管现有生成方法可处理复杂退化，但严重的信息丢失可能导致恢复结果出现语义漂移。为解决该问题，本文提出RPL-UIE，这是一个用于可靠先验学习的两阶段教师-学生框架。在教师阶段，网络从配对的退化图像与参考图像中学习表征外观和光度特性的可靠且互补的空间先验。在学生阶段，网络仅以退化图像为输入，学习模拟教师的先验提取能力，从而在推理阶段无需参考图像即可为增强过程提供更可靠的恢复指导。为缩小教师与学生模型之间的先验学习差异，本文进一步开发了残差先验细化扩散（RPRD）和频率感知先验残差校准（FPRC）。RPRD以粗先验为锚点，在残差空间中逐步预测必要的修正；FPRC保留稳定的低频残差分量，选择性调制高频细节残差，生成校准后的先验以支持高质量重建。在多个UIE基准上的实验显示了具有竞争力的恢复性能；下游的水下目标检测和实例分割实验进一步证明了增强图像在视觉感知方面的实用性提升，而对遥控潜水器（ROV）采集的真实世界数据的测试则验证了RPL-UIE的实际适用性。
英文摘要
Underwater image enhancement (UIE) aims to recover clear images from observations affected by wavelength-dependent absorption, scattering, and spatially nonuniform degradation. Although existing generative methods can handle complex degradations, severe information loss may lead to semantic drift in the restored results. To address this issue, we propose RPL-UIE, a two-stage teacher--student framework for reliable prior learning. In the teacher stage, the network learns reliable and complementary spatial priors characterizing appearance and photometric properties from paired degraded and reference images. In the student stage, the network takes only degraded images as input and learns to emulate the teacher's prior extraction capability, thereby providing more reliable restoration guidance for the enhancement process without requiring reference images at inference. To reduce the prior-learning discrepancy between the teacher and student models, we further develop Residual Prior Refinement Diffusion (RPRD) and Frequency-Aware Prior Residual Calibration (FPRC). RPRD uses the coarse priors as anchors and progressively predicts the necessary corrections in the residual space. FPRC retains stable low-frequency residual components and selectively modulates high-frequency detail residuals, producing calibrated priors to support high-quality reconstruction. Experiments on multiple UIE benchmarks demonstrate competitive restoration performance. Downstream underwater object detection and instance segmentation experiments further demonstrate the improved utility of enhanced images for visual perception, while tests on real-world data captured by a remotely operated vehicle (ROV) support the robustness and practical applicability of RPL-UIE.
Comments34 pages, 10 figures, and 6 tables
