Boosting Unsupervised Monocular Depth Estimation with Auxiliary Semantic Information

来源 :中国通信 | 被引量 : 0次 | 上传用户:pptcwu
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
Learning-based multi-task models have been widely used in various scene understanding tasks, and complement each other, i.e., they allow us to consider prior semantic information to better infer depth. We boost the unsupervised monocular depth estimati
其他文献
“十三五”期间,我国轮胎行业响应高质量发展和“一带一路”倡议,在技术创新、结构优化、绿色发展、智能制造、品牌建设、节能环保和国际化发展等方面取得了显著成绩,轮胎产
期刊
山东豪迈机械科技股份有限公司作为轮胎模具行业的龙头企业,近年来认真思考模具行业提质增效的问题,通过对模具制造行业的特点和传统模具质量管理方法进行总结和提炼,率先在
期刊
介绍315/60R22.5雪地轮胎的设计。模具设计:外径960mm,断面宽320mm,行驶面宽270mm,行驶面弧度高12mm,胎圈着合直径569.8mm,着合宽度266mm,断面水平轴位置(H1/H2)0.856,胎面采用混合型花纹,3D钢片设计,花纹深度22mm。施工设计:胎体采用0.22+(6+12)×0.20HT钢丝帘线,采用0°带束层结构,1#、2#带束层采用3+8×0.33HT钢丝帘线,密度为45根/100cm;3#带束层采用5
Network virtualization(NV)is a highprofile way to solve the ossification problem of the nowadays Internet,and be able to support the diversified network naturally.In NV,Virtual Network Embedding(VNE)problem has been widely considered as a crucial issue,wh
介绍12.00R20矿山专用全钢子午线轮胎的设计.结构设计:外直径1132mm,断面宽312mm,行驶面宽度255mm,行驶面弧度高h=8mm,胎圈着合直径511mm,胎圈着合宽度230mm,胎面采用块状花
工业互联网是新一代信息通信技术与工业经济深度融合的全新工业生态、关键基础设施和新型应用模式。它以网络为基础、平台为中枢、数据为要素、安全为保障,通过对人、机、物全面连接,变革传统制造模式、生产组织方式和产业形态,构建起全要素、全产业链、全价值链全面连接的新型工业生产制造和服务体系,对支撑制造强国,提升产业链现代化水平,推动经济高质量发展和构建新发展格局,都具有十分重要的意义。
In this paper, we provide a new approach for intelligent traffic transportation in the intelligent vehicular networks, which aims at collecting the vehicles locations, trajectories and other key drivi
This paper proposes a Reinforcement learning(RL)algorithm to find an optimal schedul-ing policy to minimize the delay for a given energy constraint in communica
With the in-depth application of new technologies such as big data in education fields,the storage and sharing model of student education records data still faces many challenges in terms of privacy protection and efficient transmission.In this paper,we p
In urban Vehicular Ad hoc Networks(VANETs),high mobility of vehicular environment and frequently changed network topology call for a low delay end-to-end routing algorithm.In this paper,we propose a Multi-Agent Reinforcement Learning(MARL)based decentrali