差异特征注意力引导的偏振图像高光移除
Differential feature attention guided polarized image highlight removal
袁东 1张健 1余洋洋 1张志良2
作者信息
- 1. 山东省水利勘测设计院有限公司济南市数字孪生与智慧水利重点实验室,山东济南 250013
- 2. 山东省水利勘测设计院有限公司济南市数字孪生与智慧水利重点实验室,山东济南 250013;河海大学信息学部信息科学与工程学院智能视觉感知实验室,江苏常州 213200
- 折叠
摘要
针对光照不均匀或者工件光滑反光材质导致的产生高亮光斑问题,提出差异特征注意力引导的偏振图像高光区域去除算法,采用两阶段式网络结构来获取高质量的高光去除结果.第一阶段利用U-Net网络提取多层次高低级特征;第二阶段设计差异特征注意力引导模块,在特征空间中建立镜面反射和漫反射间的相关性模型,补充增强漫反射层图像原始特征.此外,制作了用于偏振去高光的数据集来验证网络性能.定量和定性实验表明提出的算法去高光能力优于现有算法.
Abstract
In response to the problem of generating bright spots caused by uneven lighting or smooth reflective mate-rials on the workpiece,a differential feature attention guided polarization image highlight region removal algorithm is pro-posed,which uses a two-stage network structure to obtain high-quality highlight removal results.The first stage utilizes U-Net network to extract multi-level high-level and low-level features;In the second stage,a differential feature attention guidance module is designed to establish a correlation model between specular reflection and diffuse reflection in the fea-ture space,supplementing and enhancing the original features of the diffuse reflection layer image.In addition,a dataset for polarization highlight removal was produced to verify network performance.Quantitative and qualitative experiments have shown that the proposed algorithm has a better ability to remove highlights than existing algorithms.
关键词
光谱学/偏振成像/高光移除/两阶段网络/差异特征注意力/U-Net网络Key words
spectroscopy/polarized imaging/specular removal/two-stage network/differential feature attention/U-Net network引用本文复制引用
基金项目
济南市数字孪生与智蕙水利重点实验室开放研究基金(37H2022KY040116)
出版年
2024
NETL
NSTL
万方数据