| 自适应融合层级特征的混合退化图像复原算法 |
| |
| 引用本文： | 白亮,刘辉,尚振宏.自适应融合层级特征的混合退化图像复原算法[J].计算机辅助设计与图形学学报,2021,33(2):215-222. |
| |
| 作者姓名： | 白亮 刘辉 尚振宏 |
| |
| 作者单位： | 昆明理工大学信息工程与自动化学院 昆明 650500;昆明理工大学信息工程与自动化学院 昆明 650500;中国科学院云南天文台 昆明 650216;昆明理工大学信息工程与自动化学院 昆明 650500;昆明理工大学云南省人工智能重点实验室 昆明 650500 |
| |
| 基金项目： | 云南省重大科技专项计划;国家自然科学基金 |
| |
| 摘 要： | 多种退化类型混合的图像比单一类型的退化图像降质更严重,很难建立精确模型对其复原,研究端到端的神经网络算法是复原的关键.现有的基于操作选择注意力网络的算法(operation-wise attention network,OWAN)虽然有一定的性能提升,但是其网络过于复杂,运行较慢,复原图像缺乏高频细节,整体效果也有提升...
|
| 关 键 词： | 自适应复原 混合退化 层级特征融合 感知损失 |
Mixed Degraded Image Restoration Algorithm Based on Adaptive Fusion of Hierarchical Features |
| |
| Bai Liang,Liu Hui,Shang Zhenhong.Mixed Degraded Image Restoration Algorithm Based on Adaptive Fusion of Hierarchical Features[J].Journal of Computer-Aided Design & Computer Graphics,2021,33(2):215-222. |
| |
| Authors: | Bai Liang Liu Hui Shang Zhenhong |
| |
| Affiliation: | (Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500;Yunnan Observatories,Chinese Academy of Sciences,Kunming 650216;Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500) |
| |
| Abstract: | The degradation of mixed degraded images is more serious than that of single degradation types,and it is difficult to restore them by precise modeling.The key to restore mixed degraded images is to study the end-to-end neural network algorithm.Although the existing operation-wise attention network(OWAN)algorithm has a certain performance improvement,its network is too complex,it runs slowly,the restored image lacks high-frequency details,and the overall effect also has room for improvement.To solve these problems,an adaptive restoration algorithm based on hierarchical feature fusion is proposed.The algorithm directly fuses the features of different receptive field branches to enhance the structure of the restored image.The attention mechanism is used to dynamically fuse the features of different hierarchies to increase the adaptability and reduce the redundancy of the model.In addition,combining the L1 loss and perception loss,the visual perception effect of the restored image is enhanced.Experimental results on DIV2K,BSD500 and other data sets show that the proposed algorithm is better than the OWAN algorithm in terms of quantitative analysis of peak signal-to-noise ratio(PSNR)and structural similarity(SSIM),as well as subjective visual quality. |
| |
| Keywords: | adaptive restoration mixed degradation hierarchical feature fusion perceptual loss |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
