智能系统学报2023，Vol.18Issue(6)：1185-1196,12.DOI:10.11992/tis.202304038
基于物理先验的深度特征融合水下图像复原
Deep feature fusion for underwater-image restoration based on physical priors
摘要
Abstract
Due to interference factors such as suspended impurities of plankton and varying spectral absorption rates in an underwater environment,underwater images often suffer from degradation issues such as image blur,color distortion,and uneven illumination.This paper proposes an underwater-image reconstruction model that combines physical ima-ging principles with data-driven deep-learning methods.Using a deep neural network to infer the learnable parameters in the physical imaging model,the model generates data-driven restoration feature maps and physically informed restora-tion feature maps through modulated convolution and prior physical knowledge,respectively.Deep feature fusion with a mixed-attention mechanism is introduced to reconstruct the final image.Experimental results showed that this method can reduce noise,improve contrast,and restore image details,enhancing the visual quality and target detection accuracy of underwater images and increasing the robustness and generalizability of the underwater learning model.关键词
深度学习/水下图像恢复/神经网络/信息分离/编码器/解码器/特征提取/图像融合Key words
deep learning/underwater-image restoration/neural networks/information separation/encoder/decoder/feature extraction/image fusion分类
计算机与自动化引用本文复制引用
张心祎,谭耀,邢向磊..基于物理先验的深度特征融合水下图像复原[J].智能系统学报,2023,18(6):1185-1196,12.基金项目
国家自然科学基金项目(62076078,61703119). （62076078,61703119）
