Multilevel Disparity Reconstruction Network for Real-Time Stereo Matching  

作　　者：LIU Zhuoran ZHAO Xu 刘卓然;赵旭(School of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai,200240,China)

机构地区：[1]School of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai,200240,China

出　　处：《Journal of Shanghai Jiaotong university(Science)》2022年第5期715-722,共8页上海交通大学学报（英文版）

摘　　要：Recently,stereo matching algorithms based on end-to-end convolutional neural networks achieve excellent performance far exceeding traditional algorithms.Current state-of-the-art stereo matching networks mostly rely on full cost volume and 3D convolutions to regress dense disparity maps.These modules are computationally complex and high consumption of memory,and difficult to deploy in real-time applications.To overcome this problem,we propose multilevel disparity reconstruction network,MDRNet,a lightweight stereo matching network without any 3D convolutions.We use stacked residual pyramids to gradually reconstruct disparity maps from low-level resolution to full-level resolution,replacing common 3D computation and optimization convolutions.Our approach achieves a competitive performance compared with other algorithms on stereo benchmarks and real-time inference at 30 frames per second with 4×104 resolutions.

关 键 词：stereo matching disparity reconstruction REAL-TIME stacked residual pyramid 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]