彩色图像多尺度引导的深度图像超分辨率重建  

Color image multi-scale guided depth image super-resolution reconstruction

作　　者：于淑侠 胡良梅[1] 张旭东[1] 付绪文 Yu Shuxia;Hu Liangmei;Zhang Xudong;Fu Xuwen(School of Computer and Information,Hefei University of Technology,Hefei,Anhui 230601,China)

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230601

出　　处：《光电工程》2020年第4期40-49,共10页Opto-Electronic Engineering

基　　金：国家自然科学基金资助项目(61876057)。

摘　　要：为获得更优的深度图像超分辨率重建结果,本文构建了彩色图像多尺度引导深度图像超分辨率重建卷积神经网络。该网络使用多尺度融合方法实现高分辨率(HR)彩色图像特征对低分辨率(LR)深度图像特征的引导,有益于恢复图像细节信息。在对LR深度图像提取特征的过程中,构建了多感受野残差块(MRFRB)提取并融合不同感受野下的特征,然后将每一个MRFRB输出的特征连接、融合,得到全局融合特征。最后,通过亚像素卷积层和全局融合特征,得到HR深度图像。实验结果表明,该算法得到的超分辨率图像缓解了边缘失真和伪影问题,有较好的视觉效果。In order to obtain better super-resolution reconstruction results of depth images,this paper constructs a multi-scale color image guidance depth image super-resolution reconstruction convolutional neural network.In this paper,the multi-scale fusion method is used to realize the guidance of high resolution(HR)color image features to low resolution(LR)depth image features,which is beneficial to the restoration of image details.In the process of extracting features from LR depth images,a multiple receptive field residual block(MRFRB)is constructed to extract and fuse the features of different receptive fields,and then connect and fuse the features of each MRFRB output to obtain global fusion features.Finally,the HR depth image is obtained through sub-pixel convolution layer and global fusion features.The experimental results show that the super-resolution image obtained by this method alleviates the edge distortion and artifact problems,and has better visual effects.

关 键 词：深度图像 超分辨率重建 卷积神经网络 多尺度引导 多感受野特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]