QQ客服 官方微博 反馈留言

	Dynamic Guided Network for Monocular Depth Estimation
	Xing, Xiaoxia1,2; Cai, Yinghao2; Wang, Yanqing2; Lu, Tao2; Yang, Yiping2; Wen, Dayong2
	2021-05
会议日期	Jan. 10-15, 2021
会议地点	Milan, Italy
关键词	Depth estimation Dynamic guide filter Self-attention mechanism
DOI	10.1109/ICPR48806.2021.9413264
英文摘要	Self-attention and encoder-decoder have been widely used in the deep neural network for monocular depth estimation. The self-attention mechanism is capable of capturing long-range dependencies by computing the representation of each image position by a weighted sum of the features at all positions, while the encoder-decoder can capture detailed structural information by gradually recovering spatial information. In this work, we combine the advantages of both methods. Specifically, our proposed model, DGNet, extends EMANet by adding an effective decoder module to progressively refine the coarse depth map. In the decoder stage, we design a dynamic guided upsampling module that employs dynamically generated kernel conditioned on low-level features to guide the upsampling of the coarse depth map. Experimental results demonstrate that our method obtains higher accuracy and generates visually pleasant depth maps.
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/48782]
专题	综合信息系统研究中心_视知觉融合及其应用
通讯作者	Cai, Yinghao
作者单位	1.University of Chinese Academy of Sciences, Beijing, China 2.Institute of Automation, Chinese Academy of Sciences, Beijing, China
推荐引用方式 GB/T 7714	Xing, Xiaoxia,Cai, Yinghao,Wang, Yanqing,et al. Dynamic Guided Network for Monocular Depth Estimation[C]. 见:. Milan, Italy. Jan. 10-15, 2021.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。