Edge enhanced depth perception with binocular meta-lens

作     者：Xiaoyuan Liu Jingcheng Zhang Borui Leng Yin Zhou Jialuo Cheng Takeshi Yamaguchi Takuo Tanaka Mu Ku Chen 

作者机构：Department of Electrical Engineering City University of Hong Kong Centre for Biosystems Neuroscienceand Nanotechnology City University of Hong Kong The State Key Laboratory of Terahertz and Millimeter Waves and Nanotechnology City University of Hong Kong Innovative Photon Manipulation Research TeamRIKEN Center for Advanced Photonics Metamaterial Laboratory RIKEN Cluster for Pioneering Research Institute of Post-LED Photonics Tokushima University 

出 版 物：《Opto-Electronic Science》 (光电科学(英文))

年 卷 期：2024年第09期

页      面：6-16页

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0803[工学-光学工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：financial supports from the Research Grants Council of the Hong Kong Special Administrative Region, China [Project No. C503122G City U11310522 City U11300123] the Department of Science and Technology of Guangdong Province [Project No. 2020B1515120073] City University of Hong Kong [Project No. 9610628] JST CREST (Grant No. JPMJCR1904) 

摘      要：The increasing popularity of the metaverse has led to a growing interest and market size in spatial computing from both academia and industry. Developing portable and accurate imaging and depth sensing systems is crucial for advancing next-generation virtual reality devices. This work demonstrates an intelligent, lightweight, and compact edge-enhanced depth perception system that utilizes a binocular meta-lens for spatial computing. The miniaturized system comprises a binocular meta-lens, a 532 nm filter, and a CMOS sensor. For disparity computation, we propose a stereo-matching neural network with a novel H-Module. The H-Module incorporates an attention mechanism into the Siamese network. The symmetric architecture, with cross-pixel interaction and cross-view interaction, enables a more comprehensive analysis of contextual information in stereo images. Based on spatial intensity discontinuity, the edge enhancement eliminates illposed regions in the image where ambiguous depth predictions may occur due to a lack of texture. With the assistance of deep learning, our edge-enhanced system provides prompt responses in less than 0.15 seconds. This edge-enhanced depth perception meta-lens imaging system will significantly contribute to accurate 3D scene modeling, machine vision, autonomous driving, and robotics development.