• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of visual communication & image representation >S&CNet: A lightweight network for fast and accurate depth completion
【24h】

S&CNet: A lightweight network for fast and accurate depth completion

机译：S＆CNET：用于快速准确深度完成的轻量级网络

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Dense depth completion is essential for autonomous driving and robotic navigation. Existing methods focused on attaining higher accuracy of the estimated depth, which comes at the price of increasing complexity and cannot be well applied in a real-time system. In this paper, a coarse-to-fine and lightweight network (S&CNet) is proposed for dense depth completion to reduce the computational complexity with negligible sacrifice on accuracy. A dual-stream attention module (S&C enhancer) is proposed according to a new finding of deep neural network-based depth completion, which can capture both the spatial-wise and channel-wise global range information of extracted features efficiently. Then it is plugged between the encoder and decoder of the coarse estimation network so as to improve the performance. The experiments on KITTI dataset demonstrate that the proposed approach achieves competitive result with respect to state-of-the-art works but via an almost four times faster speed. The S&C enhancer can also be easily plugged into other existing works to boost their performances significantly with negligible additional computations.
机译：密集深度完成对于自主驾驶和机器人导航至关重要。现有方法专注于估计深度的更高准确性，以越来越复杂的价格而言，在实时系统中不能很好地应用。在本文中，提出了一种粗细和轻质网络（S＆CNET），用于密集深度完成，以降低可忽略的准确性牺牲的计算复杂性。根据基于深度神经网络的深度完成的新发现，提出了一种双流注意模块（S＆C Enhancer），其可以有效地捕获所提取的特征的空间和通道全局范围信息。然后将其插入粗估计网络的编码器和解码器之间，以提高性能。基蒂数据集的实验表明，拟议的方法在最先进的作品方面实现了竞争力，而是通过速度速度速度近四倍。 S＆C Enhancer也可以轻松插入其他现有工程以显着提高其性能，额外的额外计算。

著录项

  • 来源
    《Journal of visual communication & image representation》 |2021年第8期|103220.1-103220.12|共12页
  • 作者

    Liu Ziyang; Zhang Lei; Chen Weihai; Wu Xingming; Li Zhengguo;

  • 作者单位

    Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China|Beihang Univ Hangzhou Innovat Inst Hangzhou 310051 Peoples R China;

    Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China|Beihang Univ Hangzhou Innovat Inst Hangzhou 310051 Peoples R China;

    Shandong Univ Sci & Technol Coll Elect Engn & Automat Qingdao 266590 Peoples R China;

    Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China|Beihang Univ Hangzhou Innovat Inst Hangzhou 310051 Peoples R China|Inst Infocomm Res SRO Dept Singapore 138632 Singapore;

    Inst Infocomm Res SRO Dept Singapore 138632 Singapore;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Dense depth completion; Lightweight network; Coarse-to-fine; Attention module;

    机译：密集深度完成;轻量级网络;粗 - 细腻;注意模块;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号