.png){kind=icon}
返回
GCNDepth: Self-supervised monocular depth estimation based on graph convolutional network
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2022.10.073.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Depth estimation is a challenging task of 3D reconstruction to enhance the accuracy sensing of environ-ment awareness. This work brings a new solution with improvements, which increases the quantitative and qualitative understanding of depth maps compared to existing methods. Recently, convolutional neural networks (CNN) have demonstrated their extraordinary ability to estimate depth maps from monocular videos. However, traditional CNN does not support a topological structure, and they can work only on regular image regions with determined sizes and weights. On the other hand, graph convolu-tional networks (GCN) can handle the convolution of non-Euclidean data, and they can be applied to irregular image regions within a topological structure. Therefore, to preserve object geometric appear-ances and objects locations in the scene, in this work, we aim to exploit GCN for a self-supervised monoc-ular depth estimation model. Our model consists of two parallel auto-encoder networks: the first is an auto-encoder that will depend on ResNet-50 and extract the feature from the input image and on multi-scale GCN to estimate the depth map. In turn, the second network will be used to estimate the ego-motion vector (i.e., 3D pose) between two consecutive frames based on ResNet-18. The estimated 3D pose and depth map will be used to construct the target image. A combination of loss functions related to photometric, reprojection, and smoothness is used to cope with bad depth prediction and pre-serve the discontinuities of the objects. Our method and performance are improved quantitatively and qualitatively. In particular, our method provided comparable and promising results with a high predic-tion accuracy of 89% on the publicly available KITTI dataset. Our method also offers 40% reduction in the number of trainable parameters compared to the state of the art solutions.In addition, we tested our trained model with Make3D dataset to evaluate the trained model on a new dataset with low reso-lution images. The source code is publicly available at (https://github.com/ArminMasoumian/GCNDepth. git)(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Deep learning
Graph convolutional network
Monocular depth estimation
Self -supervision
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Seismic profiles of the offshore Gulf of Alaska Tertiary Province, R/V Thompson, Sept.-Oct. 1974
OAAI
OAAI分享收藏Monocular Depth Estimation Based on Multi-Scale Graph Convolution Networks基于多尺度图卷积网络的单目深度估计.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容